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

    Neuronpedia

    INDEX
    Explanations

    measurements including specific values with decimals

    oai_token-act-pair · gpt-3.5-turbo

    references to numerical values or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elia
    -0.64
    pty
    -0.61
     Humph
    -0.58
     Heist
    -0.58
    swick
    -0.58
    idence
    -0.57
     Osw
    -0.56
    strings
    -0.55
    ĸļ
    -0.54
    icol
    -0.54
    POSITIVE LOGITS
    Thirty
    0.91
     lakh
    0.83
    GHz
    0.81
    0000
    0.80
     million
    0.79
    inch
    0.78
     crore
    0.78
    ths
    0.78
    mL
    0.77
    âĢ³
    0.77
    Act Density 0.038%

    No Known Activations