"Thoughts are thinkers"

William James aphorism cited by Levin to support the idea that thought forms possess minimal agency rather than being purely passive data.

Neighborhood — ranked by edge-count

thinker

William James
authored
Philosopher cited for the principle 'thoughts are thinkers'—foundational to Levin's framework of active memory.

concept

Polycomputation
supports
Biological architecture where multiple competing/cooperating multi-scale agents develop interpretations of molecular and biophysical states rather than committing to single interpretation.

hypothesis

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.

Thoughts As Agentsconcept0.804
Core assertion extending William James: thoughts are not passive but active agents that facilitate their own transformation and remapping in cognitive systems.
Can machines think? This should begin with definitions of the meaning of the terms machine and think.quote0.778
Foundational epigraph setting the paper's methodological stance on conceptual clarity.
Thinking stepsconcept0.774
Segments of reasoning separated by \n\n tokens used as the unit of analysis in ReflCtrl
thought detectionconcept0.770
Task of detecting a model's internal thoughts; found by Lindsey (2026) to peak at ~2/3 depth in transformers.
"Our life is shaped by our mind; we become what we think."quote0.762
Gautama Buddha epigraph at §BODY PATTERNING AND COGNITION, thematically connecting mindfulness to embodied self-formation.
Distinguishing thoughts from text taskmethod0.751
Task where the model must simultaneously identify an injected thought and transcribe a text sentence.
chain-of-thoughtconcept0.750
A technique that outputs intermediate reasoning steps, used here to detect verbalized eval awareness.
Injected thoughts taskmethod0.749
Experimental paradigm where the model is told about the possibility of thought injection and asked to report detection and identification.