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

    Neuronpedia

    INDEX
    Explanations

    expressions of desire, inclination, and decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icket
    -0.15
    arios
    -0.15
    isse
    -0.15
    astle
    -0.15
    adelphia
    -0.14
    jed
    -0.14
    seau
    -0.14
    aurants
    -0.14
    Ùİد
    -0.14
    Ļ¨
    -0.14
    POSITIVE LOGITS
    erti
    0.18
    گز
    0.16
     -*-č↵
    0.15
    ÏĦι
    0.14
     Ogre
    0.14
    oger
    0.14
     trải
    0.14
    etur
    0.13
    åºŃ
    0.13
    >Main
    0.13
    Act Density 0.203%

    No Known Activations