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

    Neuronpedia

    INDEX
    Explanations

    key terms and phrases that indicate factual statements or assertions

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

    reality or action occurrence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ACHUSET
    -0.54
    ⤹
    -0.53
     للمعارف
    -0.53
    SharedCtor
    -0.52
     propOrder
    -0.52
    InputBorder
    -0.52
    principalColumn
    -0.52
     defaultstate
    -0.51
    juvant
    -0.49
    ousal
    -0.48
    POSITIVE LOGITS
    actually
    1.13
     actually
    1.12
     Actually
    1.09
    Actually
    1.09
    Actual
    0.97
     ACTUALLY
    0.96
     actual
    0.96
     Actual
    0.90
    actual
    0.88
     ACTUAL
    0.85
    Act Density 0.057%

    No Known Activations