gwern comments on The Dark Arts of Tokenization or: How I learned to start worrying and love LLMs’ undecoded outputs

[gwern]

There’s no reason whatsoever to think that they are independent of each other. The very fact that you can classify them systematically as ‘positive’ or ‘negative’ valence indicates they are not and you don’t know what ‘raw chance’ here yields. It might be quite probable.

[plex]

Right, I think that’s the hypothesis I was asking whether you had when I said

unless you mean the randomness was in an underlying valance factor?

If so, yeah, this is compatible. I’d still put notably higher odds on the original thing I suggested, but this is the other main hypothesis.