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

    Neuronpedia

    INDEX
    Explanations

    mentions of various authors and their contributions in research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    upe
    -0.15
    agus
    -0.14
    unya
    -0.14
    azzi
    -0.14
    kap
    -0.14
    deniz
    -0.13
    нам
    -0.13
    istik
    -0.13
    ynos
    -0.13
    dealloc
    -0.13
    POSITIVE LOGITS
     Challenger
    0.15
     Gor
    0.14
     pers
    0.14
     Nug
    0.13
    /to
    0.13
     Bounty
    0.13
     warrant
    0.13
     Rowe
    0.13
    ova
    0.13
    (tm
    0.12
    Act Density 0.123%

    No Known Activations