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

    Neuronpedia

    INDEX
    Explanations

    mentions of awards and award-winning attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     award
    -0.31
     Awards
    -0.30
     awards
    -0.30
    award
    -0.29
     Award
    -0.29
    Award
    -0.28
    å¥ĸ
    -0.22
    çįİ
    -0.20
     awarded
    -0.18
    nun
    -0.17
    POSITIVE LOGITS
    -winning
    0.39
    ing
    0.25
     winning
    0.21
    -win
    0.19
     ceremony
    0.18
    win
    0.17
    edly
    0.17
     Ceremony
    0.17
    able
    0.17
     Winning
    0.17
    Act Density 0.042%

    No Known Activations