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

    Neuronpedia

    INDEX
    Explanations

    references to changes over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stdClass
    -0.18
    ัà¸Ļà¸ĺ
    -0.17
     Bened
    -0.17
    eria
    -0.16
    fs
    -0.15
    abo
    -0.15
    uhe
    -0.14
    ãĥ¼ãĥĸãĥ«
    -0.14
    ahoma
    -0.14
    urgeon
    -0.14
    POSITIVE LOGITS
    indr
    0.15
    former
    0.14
    767
    0.14
     Zaman
    0.13
    Writes
    0.13
     IHttp
    0.13
    ÑĤÑı
    0.13
    ovny
    0.13
    anko
    0.13
    endo
    0.13
    Act Density 0.003%

    No Known Activations