Unverified50% confidenceOpinionExact time
Cammarata proposes the theory of recursive generalization, arguing that neurons gradually expand their responses along continuous dimensions of semantic or perceptual features during training, leading to apparent polysemanticity.
1
Sources
50%
Confidence
Long-term
Relevance
10/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe core idea of Hebbian learning is summarized as "neurons that fire together, wire together," requiring only the local activation states of neurons on both sides of a synapse to complete weight updates.73% similarVerifiedInterpretability research from MIT and Anthropic found that there are large numbers of polysemantic features inside models, with a single neuron potentially responding simultaneously to multiple seemingly unrelated semantic concepts.72% similarVerifiedMechanistic interpretability attempts to understand what concepts each neuron and each layer's connections encode inside a neural network.70% similarUnverifiedThere exists a study titled 'Emergent Symbolic Structures in Artificial Neural Networks,' focusing on whether neural networks spontaneously form symbolic structures similar to human cognition during training.69% similarUnverified神经网络层数越多、神经元越多，模型的表达能力越强，但也越容易出现过拟合69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1045661API
curl https://kongchang.com/api/v1/knowledge/claims/1045661MCP
get_claim(id=1045661)