It is, though. Nobody said anything about playing well, or learning the rules. The very fact that it had a valid internal representation of the game state means it's extrapolated beyond token-level. Which is the point.
Hardly, decoding “Bob picked up an Apple.” requires you to make an association between the token Bob and the token Apple. But that doesn’t imply a LLM is operating above the token level.
And again it failed to make strictly correct moves because its internal representation of the game state was flawed. Objectively an LLM when specifically trained on Othello a game with very simple and completely mechanical rules failed to abstract what those rules actually where.
The internal representation was a literal 8x8 grid of piece locations they could externally change and have it generate moves consistent with the changed position. It's about the clearest example of a learned higher-level internal representation I can think I've seen.
The fact that it didn't also perfectly learn the rules while it was doing that is entirely uninteresting.
The Othello paper is hardly a counter example. Researchers created an Othello specific model that almost learned the grammar of Othello not how to play well. Yes, there was largely correct internal game state built up from past moves. No it didn’t actually learn the rules so it would make strictly legal moves nor did it learn to make good moves.
I don’t bring up this inaccuracy because it actually makes much of a difference to playing Othello, but rather to illustrate how these systems are designed to get really good at faking things. There’s approaches that allow AI to actually learn to play arbitrary games, but they differ by having iterative feedback rather than simply providing a huge corpus. It’s like science vs philosophy, feedback prunes incorrect assumptions.