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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     exerce
    0.83
     увеличи
    0.81
     faults
    0.79
     angezeigt
    0.79
    FILE
    0.78
     rápidamente
    0.77
     welke
    0.77
    НИ
    0.76
     momencie
    0.75
    ovací
    0.75
    POSITIVE LOGITS
    想
    0.72
    Book
    0.72
    sun
    0.71
    song
    0.66
     صد
    0.65
    sis
    0.63
    尔
    0.63
    syair
    0.61
     Book
    0.59
    songs
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.