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

    Neuronpedia

    INDEX
    Explanations

    references to specific movie titles

    oai_token-act-pair · gpt-3.5-turbo

    references to various "ages" or periods in storytelling or film

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mie
    -0.80
    bledon
    -0.80
    unal
    -0.78
    clip
    -0.77
    TY
    -0.75
    iguous
    -0.73
    itably
    -0.73
    pleted
    -0.72
    orable
    -0.72
    mercial
    -0.71
    POSITIVE LOGITS
     Age
    1.08
    Age
    0.91
     Inquisition
    0.81
     Decay
    0.79
     Empires
    0.78
     Struggle
    0.75
     Restrict
    0.75
     Catalog
    0.73
     Journals
    0.72
     Discrimination
    0.71
    Act Density 0.015%

    No Known Activations