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

    Neuronpedia

    INDEX
    Explanations

    references to research studies and academic citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    intl
    -0.14
    elho
    -0.14
     arson
    -0.13
    criptive
    -0.13
     alone
    -0.13
     mand
    -0.12
    olas
    -0.12
     dÆ°Æ¡ng
    -0.12
    list
    -0.12
    285
    -0.12
    POSITIVE LOGITS
    Ìģt
    0.15
    /TT
    0.14
    .viewer
    0.13
    CPF
    0.13
     novel
    0.13
     LoggerFactory
    0.12
     ÙħÛĮÙĦادÛĮ
    0.12
    ãģŃ
    0.12
    -Jul
    0.12
    ạ
    0.12
    Act Density 0.017%

    No Known Activations