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

    Neuronpedia

    INDEX
    Explanations

    phrases related to data analysis, statistics, and research studies

    oai_token-act-pair · gpt-3.5-turbo

    mentions of statistical data and research findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¥
    -0.59
     [/
    -0.53
     Shares
    -0.50
    ").
    -0.50
    obin
    -0.47
     crochet
    -0.47
     Gors
    -0.47
     pad
    -0.46
    ey
    -0.46
     Ic
    -0.46
    POSITIVE LOGITS
     meanwhile
    0.77
    urred
    0.67
    whose
    0.65
     resided
    0.64
    uilt
    0.63
    thumbnails
    0.59
    responsible
    0.58
    mentioned
    0.57
     attest
    0.57
     presided
    0.57
    Act Density 1.424%

    No Known Activations