korrents

Our readingWhat is a korrent?

The more uncertain what follows a token, the more useful it is for a model to represent all relevant context on it.

Drawn from what Neel Nanda said

LLMs

What Neel Nanda actually said

  1. Neel Nanda Runs the mechanistic interpretability team at Google DeepMind
    one of my pet hypotheses is that um the more uncertainty there is about what comes after a token um the more useful it is to just represent all of the relevant info from the context

Added to korrents 9 Nov 2026 · How quotes work · Something wrong? Tell us

Do you hold this korrent?Do you also believe this?

I hold this too

Related korrents

Shared subject first, then similar wording. They may agree or disagree.

See this claim on the map