method
active
method:influence-functions

Influence Functions

An interpretability approach mentioned as one of several alternatives to the mechanistic approach taken in this paper

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

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

  • The maximum distance over which a cell alters the future fate of another cell; used to quantify the cognitive light cone.
  • Functionconcept0.752
    The practical, working aspect of a building; reinterpreted as the dynamic harmony of moving centers.
  • Framework informing path-specific objectives by identifying causal chains leading to risky behaviors
  • Alignment Functionconcept0.723
    A learnable invertible transformation in DAS that maps neural representations to a basis aligned with causal variables
  • Assignment and contents functions for state manipulation in Algol 50, from McCarthy 1963.
  • Reward Functionconcept0.718
    In RL, a scalar signal from the environment that defines the agent's goal; in active inference, reward is just another observation with associated preference.
  • Functions such as memory, attention, perception, and sentience that can be realized by diverse substrates.
  • Dependmethod0.706
    Attribute: attachment with issues of reliance, a text depending on another for meaning.