GeLU Activation Function

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

• SoLU Activation Functionframework0.804
  Prior Anthropic approach to increasing neuron monosemanticity via activation function design; found to make some neurons more interpretable at cost of others
• Activationsconcept0.686
  Internal representations of the model on which probes operate; the method uses activations to rank datapoints.
• Activation decompositionconcept0.666
  The conventional approach (e.g., SAEs, transcoders) of decomposing activations into interpretable features.
• Activation Probingconcept0.665
  Technique of reading out model beliefs from internal activations before the final answer token is generated
• Other-Referencing Activationsconcept0.662
  Latent model activations when processing inputs framed from another agent's perspective
• Softmax Activation Function as Neuronal Modelmethod0.658
  Using softmax to translate membrane potentials into firing rates, implementing lateral inhibition.
• Ion Channel Misexpression and Chemical Activationmethod0.655
  Experimental technique to induce bioelectric state changes and measure consequences for collective decision-making (morphogenesis, cancer, organ formation).
• Harness Activation Failureconcept0.655
  A failure mode where weak-tier models fail to invoke relevant harness artifacts (e.g., skills) during task solving