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

    Neuronpedia

    INDEX
    Explanations

    references to historical figures, artists, and cultural movements

    oai_token-act-pair · gpt-3.5-turbo

    names of influential historical and cultural figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    egu
    -0.80
    FIX
    -0.80
    cellent
    -0.78
    ourcing
    -0.76
    ento
    -0.75
    aii
    -0.71
    pection
    -0.71
    iminary
    -0.71
    responsive
    -0.70
    cation
    -0.69
    POSITIVE LOGITS
     Adolf
    1.56
     Napoleon
    1.49
     Leonardo
    1.45
     Gandhi
    1.43
     Theodore
    1.42
     George
    1.41
     Ferdinand
    1.41
     Margaret
    1.41
     Franz
    1.40
     Charles
    1.40
    Act Density 0.614%

    No Known Activations