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

    Neuronpedia

    INDEX
    Explanations

    the beginning of a document or a section

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.80
    ValueStyle
    -0.71
    featureID
    -0.69
    outState
    -0.67
     protoimpl
    -0.67
    GEBURTSDATUM
    -0.65
    GEBURTS
    -0.65
    دانشنامهٔ
    -0.62
    UrlResolution
    -0.58
    TestingModule
    -0.58
    POSITIVE LOGITS
    <bos>
    0.67
     الحره
    0.62
     regole
    0.56
     fausse
    0.55
     falsos
    0.54
    impianto
    0.54
     automatiques
    0.53
     فريبيس
    0.52
     použit
    0.52
     kän
    0.51
    Act Density 1.060%

    No Known Activations