Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    expressions of thought processes and beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    expressing a thought or belief

    np_acts-logits-general · gemini-2.5-flash-lite

    It detects expressions of belief or supposition—tokens indicating someone thinks, believes, or is under the impression.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    BagConstraints
    -0.61
    PyExc
    -0.57
     مشين
    -0.57
    Contours
    -0.56
    olume
    -0.49
     emphatically
    -0.47
    getic
    -0.46
     sharply
    -0.45
    nsis
    -0.45
    ̈́
    -0.44
    POSITIVE LOGITS
     thought
    0.66
     thinks
    0.60
     think
    0.54
    Thought
    0.52
     Thought
    0.52
     THOUGHT
    0.49
    thought
    0.46
     thinking
    0.46
     Think
    0.45
     THINK
    0.45
    Act Density 0.070%

    No Known Activations