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

    Neuronpedia

    INDEX
    Explanations

    phrases related to data sharing or distribution percentages

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to financial metrics and distribution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jad
    -0.86
    wcs
    -0.76
    actionDate
    -0.71
    dayName
    -0.71
    miah
    -0.70
    \\\\\\\\
    -0.68
     recip
    -0.67
    ãĤ¡
    -0.66
    ients
    -0.65
    æĦ
    -0.64
    POSITIVE LOGITS
     GDP
    0.86
     variance
    0.76
     total
    0.62
     GN
    0.61
     each
    0.61
     Dollars
    0.60
     proportional
    0.59
     eligible
    0.58
    arching
    0.58
     blame
    0.58
    Act Density 0.075%

    No Known Activations