claim
active
claim:all-neural-codes-not-just-communication-ones-could-plausibly-be-compressed-to-some-degreeAll neural codes, not just communication ones, could plausibly be compressed to some degree
Neuroscience implication.
Neighborhood — ranked by edge-count
Papers (1)
paper
- Toy Models of Superpositionmentions
Findings (1)
finding
- Computation in superposition.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Load-bearing framing of the core interpretability problem: neural networks encode algorithms in parameter matrices rather than human-readable code.
- The model's parameters considered as the actual 'code' implementing its algorithms, as opposed to human-written code.
- Supported by abs model.
- Vision statement in the conclusion.
- Central claim of the paper, supported by detailed feature analysis, human evaluation, automated interpretability of activations, and automated interpretability of logit weights
- Central hypothesis: sentience is not exclusive to neural systems; other biological substrates may achieve felt states.
- Closing statement.
- Universality hypothesis to be tested across families.