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

    Neuronpedia

    INDEX
    Explanations

    statements regarding relationships, attributes, or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    InitVars
    -0.59
     whoſe
    -0.42
     ProtoMessage
    -0.41
     NDEBUG
    -0.41
     capucha
    -0.41
    weightedMode
    -0.41
     Efq
    -0.40
    IsContent
    -0.39
     intptr
    -0.39
     FontFamily
    -0.38
    POSITIVE LOGITS
     is
    0.66
     are
    0.62
    zzleHttp
    0.59
     should
    0.59
     comes
    0.52
     can
    0.50
     must
    0.50
     may
    0.49
     began
    0.49
     will
    0.48
    Act Density 1.661%

    No Known Activations