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

    Neuronpedia

    INDEX
    Explanations

    references to academic authors and publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rosse
    -0.15
    Č↵
    -0.15
    Ø´ÙĪر
    -0.14
    erdale
    -0.14
    itore
    -0.14
    mary
    -0.14
    fir
    -0.14
    зÑĭ
    -0.14
    زش
    -0.14
    azu
    -0.14
    POSITIVE LOGITS
    elt
    0.15
    çĦ
    0.14
    impl
    0.14
    ench
    0.14
    ilater
    0.13
    ı
    0.13
     Lonely
    0.13
    ads
    0.13
    _SECURE
    0.13
    elic
    0.13
    Act Density 0.003%

    No Known Activations