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

    Neuronpedia

    INDEX
    Explanations

    statements or phrases indicating legal or technical details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    writeFieldEnd
    -0.79
     архивлан
    -0.77
    DeleteBehavior
    -0.71
    TintMode
    -0.70
    rungsseite
    -0.68
    itinéraire
    -0.68
    Sucesor
    -0.68
     Roskov
    -0.68
    หวัด
    -0.68
     насељу
    -0.64
    POSITIVE LOGITS
    gal
    0.46
    prá
    0.44
    отно
    0.44
    BASEPATH
    0.44
    stretchr
    0.42
    Lines
    0.41
     infatti
    0.41
     surla
    0.40
    Indeed
    0.39
    Parameteri
    0.38
    Act Density 0.204%

    No Known Activations