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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to places and teams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NOPQRST
    -0.67
     Romans
    -0.59
    rrggbb
    -0.56
     Commandments
    -0.56
    ameter
    -0.56
    allible
    -0.56
     Wetlands
    -0.55
     kingdoms
    -0.55
     informativo
    -0.54
    brigens
    -0.54
    POSITIVE LOGITS
    ########.
    0.80
    stdc
    0.78
    出版年
    0.66
     مرئيه
    0.63
     kaynağından
    0.62
    <bos>
    0.62
    piram
    0.61
    \{\\
    0.59
    曖昧さ回避
    0.57
    jooq
    0.56
    Act Density 0.113%

    No Known Activations