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

    Neuronpedia

    INDEX
    Explanations

    mentions or descriptions of small size or individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to small or miniature items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chwitz
    -0.83
    yrinth
    -0.79
     largeDownload
    -0.78
    inelli
    -0.73
    ilee
    -0.73
    atche
    -0.73
    lain
    -0.71
    ophen
    -0.69
    orthy
    -0.69
    ————————————————
    -0.68
    POSITIVE LOGITS
    tiny
    0.96
    pox
    0.95
     bit
    0.88
     fraction
    0.87
     tiny
    0.83
     handful
    0.82
     (<
    0.81
     fractions
    0.80
     slice
    0.78
     tad
    0.77
    Act Density 0.021%

    No Known Activations