Intentional Control of Internal States

Models can modulate their internal representations when instructed or incentivized to 'think about' a concept; effect replicates across all tested models regardless of capability.

Source paper

extracted_from

Emergent Introspective Awareness in Large Language Models

(2026) · Lindsey, Jack

Neighborhood — ranked by edge-count

Communities (3)

community

Manifold-aware concept steering in neural representations
members_of
Explores geometry of activation/behavior manifolds to enable selective, non-destructive concept interventions.
Self-correcting search in generative design
members_of
Iterative feedback steering that improves candidate success rates across materials, proteins, and drugs through internal-state control, achieving 4-6x empirical gains.
Intentional control of mental representations
members_of
Voluntary regulation of internal states by leveraging topic-directed cognitive mechanisms

Concepts (1)

concept

Accuracy Criterion
supports
Criterion requiring that model's description of internal state be accurate, distinguishing genuine introspection from confabulation.

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.

Intentional control of internal representations likely piggybacks on existing mechanisms for talking about a topicclaim0.791
Mechanism speculation for the intentional control experiment.
Intentional control taskmethod0.786
Task instructing the model to write a sentence while thinking or not thinking about a word, measuring internal representation strength.
internal states of agentconcept0.774
States that encode perceptual model and expectations; emerge naturally from free-energy optimization.
Principled Control via Intervention on Internalsconcept0.759
The goal of mechanistically-grounded, reliable control of neural network behavior via activation interventions
Internal states appear to encode Bayesian beliefs about hidden external states.claim0.756
The inferential interpretation of internal dynamics.
Stateful Internal Representationconcept0.743
A representation that maintains stable activation across many tokens rather than being locally triggered by specific content
internal emotional stateconcept0.739
The possibility of a stably encoded, causally active emotional state within LLMs, as distinct from token-by-token semantic content
principled control via internals using geometryconcept0.735
Claim that geometry enables accurate intervention; steering moves from direction-finding to geometry-finding.