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

    Neuronpedia

    INDEX
    Explanations

    numerical data, specifically numbers with 'percent' and quantity descriptions

    oai_token-act-pair · gpt-3.5-turbo

    numerical values related to quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iatrics
    -0.71
    olson
    -0.68
    bos
    -0.67
    Clar
    -0.65
    andise
    -0.65
    ffen
    -0.63
    utics
    -0.61
    bender
    -0.60
    olis
    -0.60
    uld
    -0.59
    POSITIVE LOGITS
     dozen
    1.09
     hundred
    1.07
     thousand
    0.99
    fold
    0.89
     thous
    0.86
     lakh
    0.85
    dozen
    0.83
     thirds
    0.82
     million
    0.80
    thirds
    0.77
    Act Density 0.112%

    No Known Activations