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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their formats

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.61
     AttributeSet
    -0.60
    ThroughAttribute
    -0.59
     forState
    -0.55
    {
    -0.54
    ",&
    -0.52
    GraphicsUnit
    -0.51
     kö
    -0.49
    AutoScale
    -0.49
    '];?>
    -0.48
    POSITIVE LOGITS
     RSSSF
    0.68
     dreamstime
    0.62
     auffi
    0.59
     dafs
    0.59
     ainfi
    0.59
     depositphotos
    0.59
    transQ
    0.57
     Jefus
    0.57
     فريبيس
    0.56
     ſtate
    0.56
    Act Density 0.065%

    No Known Activations