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

    Neuronpedia

    INDEX
    Explanations

    terms related to historical events, concentration camps, and political groups

    oai_token-act-pair · gpt-3.5-turbo

    topics related to historical references, particularly those concerning war and conflict, as well as themes related to societal structures and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,,,,
    -0.74
    selves
    -0.73
    enance
    -0.73
     Hawking
    -0.70
    aneously
    -0.70
    =-=-=-=-
    -0.69
     Helpful
    -0.68
     Roof
    -0.68
     Feather
    -0.67
    cies
    -0.65
    POSITIVE LOGITS
     industry
    0.95
     industries
    0.90
     bureau
    0.85
     crus
    0.84
    indust
    0.80
     brig
    0.79
     worker
    0.79
    war
    0.78
     enthusiast
    0.78
     factories
    0.78
    Act Density 0.828%

    No Known Activations