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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    {
    0.65
    9
    0.57
    Popular
    0.54
    غ
    0.54
    ت
    0.53
    自
    0.53
    Tr
    0.53
    Text
    0.53
    '
    0.52
    G
    0.52
    POSITIVE LOGITS
     выбирать
    0.50
    ском
    0.48
     ком
    0.47
    <unused205>
    0.46
    𝘦
    0.46
     выбран
    0.46
    ža
    0.46
     яхшы
    0.46
     ничек
    0.46
    ым
    0.46
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.