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

    Neuronpedia

    INDEX
    Explanations

    ratings on a scale from 1 to 5

    oai_token-act-pair · gpt-3.5-turbo

    quantitative ratings and scores

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pty
    -0.68
    elia
    -0.65
    icol
    -0.64
    quit
    -0.63
    geist
    -0.62
    stration
    -0.62
    sters
    -0.61
    strings
    -0.61
    stru
    -0.60
    ĸļ
    -0.59
    POSITIVE LOGITS
    Thirty
    0.88
     gallon
    0.80
    mL
    0.77
    GHz
    0.77
    inch
    0.75
    WD
    0.74
     lakh
    0.73
    0000
    0.72
    ths
    0.72
    MN
    0.72
    Act Density 0.041%

    No Known Activations