method
active
method:intentional-control-task

Intentional control task

Task instructing the model to write a sentence while thinking or not thinking about a word, measuring internal representation strength.

Neighborhood — ranked by edge-count

Concepts (1)

concept
  • Technique of injecting activation patterns associated with specific concepts into a model's internal states to test whether self-reports reflect ground truth.

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.

  • Adaptation of Hewitt and Liang control tasks to CausalGym: next-token labels replaced with arbitrary tokens to measure method expressivity
  • controlconcept0.794
    The act of directing a system's behavior; the objective of a regulator.
  • Models can modulate their internal representations when instructed or incentivized to 'think about' a concept; effect replicates across all tested models regardless of capability.
  • Intentional Actionconcept0.782
    Central explanatory target: behavior constrained by prior intentions and contextual constraints that emerge from cognitive reorganization.
  • Intentional Agencyconcept0.768
    Capacity to set and pursue goals via beliefs, desires, and intentions.
  • The ability of individuals and communities to shape, own, and modify their living spaces; a prerequisite for belonging
  • Task balancingconcept0.745
    The problem of ensuring all tasks in MTL perform well, avoiding dominance by some tasks.
  • Control directly priming consciousness ideation without inducing self-reference; yields near-zero experience claims