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

    Neuronpedia

    INDEX
    Explanations

    large numerical values related to costs, taxes, and earnings

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and economic statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    76561
    -0.62
    stakes
    -0.61
    oys
    -0.61
    uli
    -0.61
    osen
    -0.59
     Seas
    -0.59
     Niet
    -0.59
    girls
    -0.58
    emade
    -0.58
    angular
    -0.57
    POSITIVE LOGITS
     per
    1.26
     annually
    1.16
    -$
    0.99
     yearly
    0.87
     apiece
    0.87
     upfront
    0.83
     monthly
    0.83
     hourly
    0.80
     annual
    0.77
     subsidy
    0.76
    Act Density 0.145%

    No Known Activations