korrents

Our readingWhat is a korrent?

Information should be expected in a model's activations when it has a causal impact on the actions the model takes.

Drawn from what Neel Nanda said

What this subject means

neural networks The architecture almost all modern machine learning is built on, and what changes when it gets deeper.

What Neel Nanda actually said

  1. Neel Nanda Runs the mechanistic interpretability team at Google DeepMind
    And I would basically say you should expect it to be in the activations when it is necessary or like when it has a causal impact on the actions the model is taking.

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