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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     which
    -1.13
     that
    -0.95
    遠慮
    -0.94
    Ԫ
    -0.93
    いただいた
    -0.92
    咯
    -0.92
    minyak
    -0.91
     budget
    -0.91
     promoting
    -0.90
     previous
    -0.89
    POSITIVE LOGITS
     alcune
    1.03
    onaldo
    0.98
     evtl
    0.96
     zrobić
    0.96
    maría
    0.94
    ()));
    0.94
    ─
    0.94
    still
    0.93
     Dinas
    0.93
    женская
    0.93
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.