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

    Neuronpedia

    INDEX
    Explanations

    references to awards and accolades

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isay
    -0.17
    ults
    -0.16
    pone
    -0.15
    äll
    -0.15
    éis
    -0.15
    ickness
    -0.14
    kiye
    -0.14
    aji
    -0.14
    ÏĨÏħ
    -0.13
    ento
    -0.13
    POSITIVE LOGITS
     winning
    0.52
    -winning
    0.49
    win
    0.40
     Winning
    0.39
     win
    0.30
    Win
    0.28
    WIN
    0.28
     winner
    0.27
     winners
    0.26
     WIN
    0.26
    Act Density 0.011%

    No Known Activations