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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Hitler
    1.16
     Napoleon
    1.10
     "/
    1.09
     "[
    1.08
     Negro
    1.08
     "'
    1.07
     Jack
    1.06
     Franco
    1.05
     Denmark
    1.05
     Mis
    1.04
    POSITIVE LOGITS
    ion
    0.97
    Growing
    0.95
    Total
    0.94
    तम
    0.93
    ب
    0.91
    ن
    0.90
    Also
    0.86
    achem
    0.81
    ivation
    0.81
     एके
    0.80
    Act Density 0.000%

    No Known Activations