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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    leted
    0.47
    to
    0.46
    LE
    0.45
    >
    0.45
    time
    0.44
    legislation
    0.44
     wage
    0.43
     i
    0.43
     উ
    0.43
     mistrust
    0.43
    POSITIVE LOGITS
     Hered
    0.58
     Benutzer
    0.52
     Schreib
    0.49
    బి
    0.48
    isieren
    0.48
     Geschichte
    0.47
     Chilton
    0.47
     schrift
    0.46
     Höhen
    0.46
     honti
    0.46
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.