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

    Neuronpedia

    INDEX
    Explanations

    references to various awards and accolades

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Preceding or containing the word "award"

    np_acts-logits-general · gemini-2.0-flash

    award winning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .*")]
    -0.62
     فريبيس
    -0.56
     مفص
    -0.54
    ց
    -0.52
    UNTS
    -0.51
    PSI
    -0.50
    zuführen
    -0.48
     privacidade
    -0.48
    ities
    -0.48
    utel
    -0.47
    POSITIVE LOGITS
    winning
    1.01
     winning
    0.90
    ########.
    0.86
     Winning
    0.85
    Winning
    0.79
    0.76
     winners
    0.75
     Winners
    0.74
    winner
    0.72
     tph
    0.71
    Act Density 0.103%

    No Known Activations