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

    Neuronpedia

    INDEX
    Explanations

    references to fascism, extremism, and far-right political ideology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    溜
    -0.47
     Christmas
    -0.46
    meyi
    -0.44
    rzej
    -0.44
     rpc
    -0.44
     interess
    -0.43
     INTERESAR
    -0.42
     Mehl
    -0.42
    тифика
    -0.42
     Weihnachten
    -0.41
    POSITIVE LOGITS
     extremist
    0.98
     extré
    0.88
     extremism
    0.88
     totalitarian
    0.87
     extremists
    0.87
     extremos
    0.86
     Extrem
    0.85
     fascist
    0.81
    extré
    0.80
     Hitler
    0.79
    Act Density 0.402%

    No Known Activations