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

    Neuronpedia

    INDEX
    Explanations

    technical terminology and code structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ëĭ¤ìļ´ë°Ľê¸°
    -0.20
    istrovstvÃŃ
    -0.15
     项
    -0.14
     ëĦ¤ìĿ´íĬ¸
    -0.14
     fac
    -0.13
     å¹³æĸ¹
    -0.13
    æĮ¥
    -0.13
     freelance
    -0.13
     prostitutas
    -0.13
    gnore
    -0.13
    POSITIVE LOGITS
    avage
    0.14
    cname
    0.14
     Bbw
    0.14
    remen
    0.14
    deaux
    0.13
    ativ
    0.13
    meyi
    0.13
    vvm
    0.13
    ennai
    0.13
    azy
    0.13
    Act Density 0.061%

    No Known Activations