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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    0
    0.82
    ?
    0.77
    ic
    0.77
    3
    0.74
     améli
    0.74
     vises
    0.74
    ized
    0.73
    Type
    0.72
    '
    0.72
     semblable
    0.71
    POSITIVE LOGITS
    𝒮
    1.09
    teilung
    0.92
     Khalifa
    0.85
    ਰ
    0.84
     Kxb
    0.83
    haltung
    0.82
     КА
    0.80
    hAP
    0.79
    NESDAY
    0.78
    riera
    0.77
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.