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

    Neuronpedia

    INDEX
    Explanations

    numbers related to quantities or percentages

    oai_token-act-pair · gpt-3.5-turbo

    numeric representations of quantities, particularly those involving the numbers thirty, forty, and seventy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HC
    -0.71
    Bank
    -0.70
    earable
    -0.69
    BD
    -0.68
    Helper
    -0.68
    HY
    -0.67
    FC
    -0.67
    AC
    -0.67
    ULE
    -0.66
    KI
    -0.66
    POSITIVE LOGITS
     thousand
    1.07
     twenty
    0.99
     eighty
    0.99
     hundred
    0.98
     forty
    0.98
     thirty
    0.98
     sixty
    0.96
    eenth
    0.96
     fifty
    0.95
     thous
    0.94
    Act Density 0.011%

    No Known Activations