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

    Neuronpedia

    INDEX
    Explanations

    numerals and numerical information

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and percentages, particularly in contexts involving finance, statistics, or medical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ozone
    -0.65
     miscarriage
    -0.63
    tnc
    -0.62
     Mehran
    -0.61
    iatus
    -0.61
    isphere
    -0.60
     predicament
    -0.60
     Roundup
    -0.59
    TPPStreamerBot
    -0.59
    phrine
    -0.57
    POSITIVE LOGITS
    etheless
    0.99
    anwhile
    0.73
    emort
    0.68
    icators
    0.67
    eddy
    0.67
    ngth
    0.67
    ÅŁ
    0.66
    olas
    0.66
    theless
    0.66
    cephal
    0.65
    Act Density 0.183%

    No Known Activations