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

    Neuronpedia

    INDEX
    Explanations

    quantities and measurements related to physical properties or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     NDEBUG
    -0.66
    Personensuche
    -0.62
    complexContent
    -0.61
    racia
    -0.59
     Neither
    -0.58
     Volga
    -0.58
     trident
    -0.56
    {!
    -0.56
    Datuak
    -0.56
     dandruff
    -0.56
    POSITIVE LOGITS
     the
    0.70
     فريبيس
    0.68
     our
    0.64
     each
    0.61
     his
    0.59
     your
    0.58
     bougies
    0.57
     htmlFor
    0.54
    ρης
    0.53
    本次
    0.53
    Act Density 0.603%

    No Known Activations