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

    Neuronpedia

    INDEX
    Explanations

    references to Nazi Germany and events associated with World War II

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     }}"></
    -0.71
    oznam
    -0.68
    WithIOException
    -0.67
    hyrchwyd
    -0.66
    '))
    -0.66
     beginnetje
    -0.64
     AssemblyCompany
    -0.63
    âmetro
    -0.61
     ErrIntOverflow
    -0.61
    XmlAccessorType
    -0.61
    POSITIVE LOGITS
     Hitler
    0.84
    Hitler
    0.81
     Nazi
    0.74
     nazi
    0.65
     Führer
    0.64
     Mussolini
    0.64
     fascism
    0.60
    Nazi
    0.59
     Nazis
    0.58
    locaust
    0.58
    Act Density 0.067%

    No Known Activations