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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the importance or presence of specific subjects or concepts within discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sth
    -0.14
    ovic
    -0.14
    .ua
    -0.14
     å°
    -0.14
    Ñĭп
    -0.14
    ploy
    -0.13
     dane
    -0.13
    uyên
    -0.13
     éĻĪ
    -0.13
    bble
    -0.13
    POSITIVE LOGITS
     certain
    0.17
     Certain
    0.17
    ubre
    0.17
    ecer
    0.15
    ILON
    0.14
    eron
    0.14
     recent
    0.14
    quisitions
    0.14
    uste
    0.13
    marvin
    0.13
    Act Density 0.334%

    No Known Activations