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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     behav
    -0.69
     Constantin
    -0.65
    Var
    -0.65
    Ca
    -0.63
    Editor
    -0.63
    gate
    -0.62
     Integrity
    -0.62
    WARNING
    -0.62
     Apex
    -0.61
    personal
    -0.61
    POSITIVE LOGITS
    itaire
    0.83
    veyard
    0.82
    ylan
    0.75
    Æ
    0.71
    SHIP
    0.70
    ³³³³³³³³³³³³³³³³
    0.70
    anya
    0.69
    kefeller
    0.68
    itance
    0.68
    ahar
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.