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

    Neuronpedia

    INDEX
    Explanations

    large numerical values

    oai_token-act-pair · gpt-3.5-turbo

    numerical values related to financial amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umbn
    -0.73
    igators
    -0.64
    aders
    -0.63
    aways
    -0.63
    rist
    -0.63
    ropolitan
    -0.60
    fing
    -0.60
    landers
    -0.60
    ishes
    -0.59
    tnc
    -0.59
    POSITIVE LOGITS
    -$
    1.03
     billion
    0.96
     USD
    0.86
     Billion
    0.86
     million
    0.84
    bn
    0.82
    AUD
    0.81
    billion
    0.80
    million
    0.79
     lakh
    0.78
    Act Density 0.062%

    No Known Activations