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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    С
    0.54
    Ｓ
    0.54
    Сер
    0.54
    使用
    0.50
    Ле
    0.50
    При
    0.49
    Бу
    0.49
    Ш
    0.48
    0.48
    Че
    0.45
    POSITIVE LOGITS
    ceans
    0.56
    śa
    0.54
     istor
    0.53
    found
    0.52
    fehlung
    0.52
    ira
    0.52
    jaan
    0.52
    iner
    0.51
    conversation
    0.51
    gist
    0.51
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.