Prediction and Suppression Neuron Fraction

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• All neuronal processing and action selection minimize variational free energy, unifying perception, action, and learning.claim0.745
  Fundamental assertion: single imperative (free energy minimization) explains diverse cognitive and neural phenomena.
• Neuron cluster identification via partitioningmethod0.726
  Method used to identify and partition the 28 MLP neurons into disjoint clusters by Fourier period
• Fourier features with period 10 contribute to base-10 sum computation in the 28-neuron clusterfinding0.725
  One of the three base-10 Fourier periods identified in the sparse neuron set
• No neuron found with Hebrew Unicode block in top dataset examples; most correlated neuron A/neurons/489 has correlation of only 0.1finding0.717
  Hebrew feature is effectively invisible in the neuron basis
• Most correlated neuron A/neurons/470 has correlation of only 0.18 with base64 feature A/1/2357 and responds to code, HTML labels, URLsfinding0.717
  Shows base64 feature is polysemantic at neuron level but monosemantic as learned feature
• Arabic feature A/1/3450 has 27 neurons with coefficient magnitude ≥0.1 and three largest coefficients are negative; most correlated neuron responds to mixture of non-English languagesfinding0.713
  Demonstrates that the Arabic feature is not aligned to any single neuron
• What are the neuronal mechanisms by which prior beliefs from one agent's model are received and properly implemented by a naive agent (neuronal hermeneutics)?question0.709
  Open question about inter-agent communication beyond model-space assumption
• Neuronal dynamics for state estimation coincide with variational message passing.claim0.709
  Connection between active inference and message passing algorithms.