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

    Neuronpedia

    INDEX
    Explanations

    expressions related to awareness and its various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.73
     autorytatywna
    -0.72
     propOrder
    -0.67
     '\\;'
    -0.67
     jspb
    -0.67
     CanadaChoose
    -0.67
    تقاوى
    -0.66
    RenderAtEndOf
    -0.65
    SharedDtor
    -0.65
     faſt
    -0.65
    POSITIVE LOGITS
    via
    0.68
     via
    0.50
    Via
    0.50
    alt
    0.48
    I
    0.43
    ↵
    0.42
     Nación
    0.42
    div
    0.42
    rungs
    0.42
     +
    0.41
    Act Density 0.382%

    No Known Activations