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

    Neuronpedia

    INDEX
    Explanations

    numerical values and parameters related to testing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     (
    -0.45
    assen
    -0.45
    endra
    -0.44
    insch
    -0.43
     cận
    -0.42
    撩
    -0.42
    pie
    -0.41
    ImageBackground
    -0.41
    tetten
    -0.41
    ara
    -0.41
    POSITIVE LOGITS
     незавершена
    0.85
     disambiguazione
    0.84
     OFDb
    0.78
     الرياضيه
    0.78
    󠁴
    0.76
     ModelExpression
    0.75
    EDEFAULT
    0.74
    istoitu
    0.73
    InjectAttribute
    0.69
     HasFactory
    0.69
    Act Density 0.224%

    No Known Activations