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

    Neuronpedia

    INDEX
    Explanations

    numbers indicating quantity or amount

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of numerical values, particularly those related to quantities or ages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Activity
    -0.68
    igion
    -0.67
    Bank
    -0.67
    TPP
    -0.66
    agate
    -0.65
     Syndicate
    -0.62
    ULE
    -0.62
    guide
    -0.62
    BOOK
    -0.61
     Loans
    -0.61
    POSITIVE LOGITS
     thousand
    1.17
    eenth
    1.11
    eteen
    1.06
    teenth
    0.99
    Eight
    0.97
    teen
    0.96
     hundred
    0.91
    eight
    0.90
     Thousand
    0.90
    ieth
    0.89
    Act Density 0.030%

    No Known Activations