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

    Neuronpedia

    INDEX
    Explanations

    references to Nazi Germany and its leaders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IsContent
    -0.69
    الإنجليزية
    -0.66
     beginnetje
    -0.66
    kke
    -0.65
    ništ
    -0.63
    RenderAtEndOf
    -0.63
     发表于
    -0.63
     resourceCulture
    -0.62
    oznam
    -0.61
     input
    -0.60
    POSITIVE LOGITS
     Hitler
    1.09
     Nazi
    1.05
    Hitler
    1.00
    Nazi
    0.94
     nazi
    0.90
     fascist
    0.86
     Cæsar
    0.84
     Nazis
    0.82
     nazis
    0.78
     fascism
    0.77
    Act Density 0.027%

    No Known Activations