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

    Neuronpedia

    INDEX
    Explanations

    phrases related to communication or requests for feedback

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /cache
    -0.16
    声
    -0.16
    rat
    -0.15
     Affero
    -0.14
    رة
    -0.14
    æ¦ľ
    -0.14
    arta
    -0.14
    Ìĥ
    -0.13
     sạch
    -0.13
    inç
    -0.13
    POSITIVE LOGITS
    ëĭ´
    0.16
    edd
    0.15
    ypes
    0.15
    zym
    0.15
    rame
    0.15
    immer
    0.14
     Morav
    0.14
    ross
    0.14
    quam
    0.14
     Eld
    0.14
    Act Density 0.028%

    No Known Activations