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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     keeping
    0.83
    he
    0.76
    }
    0.75
    '
    0.75
    re
    0.74
     H
    0.73
    .
    0.71
    {
    0.70
     K
    0.69
    -
    0.69
    POSITIVE LOGITS
    сным
    1.09
    сное
    1.03
     может
    0.99
    庤
    0.96
     мастеров
    0.95
    вайтесь
    0.93
     часть
    0.92
     владель
    0.92
    ropower
    0.92
     органы
    0.92
    Act Density 0.001%

    No Known Activations