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

    Neuronpedia

    INDEX
    Explanations

    instances of punctuation

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Eſ
    -0.62
    OpenHelper
    -0.58
     Monfieur
    -0.57
    اذ
    -0.57
     Jefus
    -0.57
     ſon
    -0.56
     post
    -0.56
     translational
    -0.56
    └──
    -0.56
    ToTensor
    -0.56
    POSITIVE LOGITS
     שוליים
    0.72
     Drapeau
    0.69
    KommentareTeilen
    0.65
    __":
    0.61
     ProtoMessage
    0.60
    __':
    0.53
    InjectAttribute
    0.51
    ContentAsync
    0.51
    DoubleQuotes
    0.51
     Picchu
    0.49
    Act Density 0.004%

    No Known Activations