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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     McM
    -0.89
     Louie
    -0.74
     retard
    -0.73
    anchester
    -0.72
     Buchanan
    -0.70
     Americ
    -0.67
     mans
    -0.66
     Nanto
    -0.65
     Scalia
    -0.65
    uyomi
    -0.65
    POSITIVE LOGITS
    Leaks
    0.80
    gression
    0.73
     rewarded
    0.69
    OSP
    0.66
    765
    0.65
    fect
    0.64
    former
    0.63
     HIT
    0.63
    代
    0.62
    ENG
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.