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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating improvement or enhancement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sig
    -0.17
    roup
    -0.16
    adb
    -0.16
    sı
    -0.15
    sy
    -0.15
    cron
    -0.15
    ãģĤãģ£ãģŁ
    -0.14
    sing
    -0.14
    vfs
    -0.14
    qi
    -0.14
    POSITIVE LOGITS
    anning
    0.18
    azzi
    0.16
    дам
    0.16
    Ñĩина
    0.15
    agency
    0.15
    unger
    0.15
    ardon
    0.14
    idge
    0.14
     verst
    0.14
     Agency
    0.14
    Act Density 0.013%

    No Known Activations