Compare to https://www.lesswrong.com/posts/zXfqftW8y69YzoXLj/using-gpt-n-to-solve-interpretability-of-neural-networks-a, which is about defining how well a neural net can be described in terms of gears.
Compare to https://www.lesswrong.com/posts/zXfqftW8y69YzoXLj/using-gpt-n-to-solve-interpretability-of-neural-networks-a, which is about defining how well a neural net can be described in terms of gears.