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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically names of people or places

    oai_token-act-pair · gpt-3.5-turbo

    the names or representations of individuals, particularly those of public figures or characters in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾įå¥ij士
    -0.82
    Reviewer
    -0.68
    rawdownloadcloneembedreportprint
    -0.67
    ãĤ¤ãĥĪ
    -0.62
     Shiv
    -0.62
    ä¼
    -0.57
     Generations
    -0.57
    uscript
    -0.57
    terday
    -0.56
    REDACTED
    -0.55
    POSITIVE LOGITS
    IDA
    0.73
    vre
    0.72
    lain
    0.71
     Niet
    0.70
    isner
    0.69
    ologne
    0.66
    erve
    0.66
    ¬
    0.66
    isi
    0.65
    helle
    0.65
    Act Density 0.043%

    No Known Activations