Skip to content

Detector tell · 3 patterns · weight 2

Three adverbs that promise the sentence is about to matter

Three rows at weight 2, each matching a sentence-opening adverb followed by a comma.

Our detector calls this category “GPT-4 elevation”. The patterns below are read out of functions/api/tools/detect.js when this page is built. A match is a fact about a phrase, not about who wrote the text.

Where this phrase showed up

Did not appear in the licensed samples we checked — no human sample and no AI sample. The rule still matches text that contains its own pattern. The constructed example below is that check.

We are not going to invent an example to fill the gap. What we can show instead is a sentence we wrote ourselves, purely to check that the rule is live.

A constructed example — written by us, not evidence

This sentence was written for this check. It is not from the licensed samples, nobody wrote it as real prose, and it says nothing about how anyone writes. Its only job is to prove the rule still fires, and the generator fails the build if it stops.

“Notably, the second run finished in half the time.”

  • /\bnotably,/gi → “Notably,”

What it means when a person writes this way

These are the ordinary furniture of argument. A reviewer writes "Notably," when one result stands out; a philosopher writes "Indeed," to concede a point. The comma requirement narrows the pattern to the sentence-opening use, which is the register-marked one, but that register belongs to human essayists as much as to any model.

The patterns, as the engine holds them

3 of the 70 rows in our phrase table carry this label. They are printed here as they are written, because a paraphrase of a regular expression is a different regular expression.

/\bnotably,/gi weight 2

Matches “notably,” , in any capitalisation .

/\bindeed,/gi weight 2

Matches “indeed,” , in any capitalisation .

/\bessentially,/gi weight 2

Matches “essentially,” , in any capitalisation .

What a hit does to your score

The phrase model is one of four in our ensemble, and its formula is patternScore = min(98, max(5, 10 + 7 x total weight)). One occurrence of the heaviest row in this category takes that model from 10 to 24 out of 100 — and the pattern model carries 40% of the ensemble when the em-dash signal fires and 55% when it does not.

Weight 2 each. Unlike the formal connectors, this label has no floor of its own — three of these in a document contribute 6 to the weighted load and nothing else.

Check your own text

Our detector is free and shows you which sentences it flagged and why, including this category. Treat the score as a starting point, not proof.

Run the detector If you have been accused Why formal writing gets flagged

Other things the detector looks for