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

    Neuronpedia

    INDEX
    Explanations

    numbers with decimals

    oai_token-act-pair · gpt-3.5-turbo

    numeric data related to statistics and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    linger
    -0.71
    hess
    -0.62
    ilial
    -0.60
    ributed
    -0.59
    adobe
    -0.57
    dream
    -0.57
    asher
    -0.57
     Citiz
    -0.57
    vern
    -0.56
    parser
    -0.56
    POSITIVE LOGITS
     million
    1.25
     billion
    1.17
     percent
    1.09
    %.
    1.09
    %
    1.07
     lakh
    1.07
    %,
    1.06
    million
    1.04
     trillion
    1.03
     crore
    1.01
    Act Density 0.067%

    No Known Activations