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

    Neuronpedia

    INDEX
    Explanations

    words related to numerical figures

    oai_token-act-pair · gpt-3.5-turbo

    terms related to numerical data or figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rated
    -0.67
    angan
    -0.66
     foul
    -0.66
    bey
    -0.65
     Exit
    -0.63
     Highly
    -0.62
    INTON
    -0.62
     purity
    -0.62
     KE
    -0.62
    CHAT
    -0.62
    POSITIVE LOGITS
    fig
    1.42
    figure
    1.39
    uration
    1.10
    figured
    1.03
    table
    0.90
    lisher
    0.89
    urations
    0.88
    lio
    0.87
    uring
    0.87
     rall
    0.85
    Act Density 0.006%

    No Known Activations