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

    Neuronpedia

    INDEX
    Explanations

    references to Nazi-related terms and topics

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Nazi regime and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tis
    -0.91
    pring
    -0.88
    trak
    -0.84
    Downloadha
    -0.78
    area
    -0.78
    ately
    -0.77
    pole
    -0.77
    ional
    -0.75
    ttes
    -0.74
    oner
    -0.74
    POSITIVE LOGITS
     salute
    0.89
     sympath
    0.88
     Youth
    0.84
     paramilitary
    0.83
     Holocaust
    0.81
     propaganda
    0.81
     dictator
    0.78
     collaborator
    0.78
     Reich
    0.77
     extermination
    0.77
    Act Density 0.015%

    No Known Activations