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

    Neuronpedia

    INDEX
    Explanations

    references to Adolf Hitler

    oai_token-act-pair · gpt-3.5-turbo

    references to Adolf Hitler

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tis
    -0.82
    Medium
    -0.78
    Self
    -0.78
    Mount
    -0.76
    ilver
    -0.73
    Dub
    -0.72
    Trend
    -0.69
    teen
    -0.68
    Methods
    -0.68
    region
    -0.68
    POSITIVE LOGITS
     Hitler
    1.26
     Adolf
    0.91
    enstein
    0.91
    dinand
    0.88
     Pepe
    0.85
    geist
    0.84
    olini
    0.82
     salute
    0.82
    ocaust
    0.80
     mustache
    0.79
    Act Density 0.015%

    No Known Activations