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

    Neuronpedia

    INDEX
    Explanations

    sports-related terms and game scores

    oai_token-act-pair · gpt-3.5-turbo

    numerical statistics or scores related to games

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Clarks
    -0.72
     Borders
    -0.67
     mirrors
    -0.65
     Kyl
    -0.65
     cubes
    -0.63
     flats
    -0.63
     Lenn
    -0.62
     tents
    -0.61
     Bates
    -0.61
     Cassidy
    -0.61
    POSITIVE LOGITS
    point
    1.39
    pointer
    1.33
    game
    1.30
    run
    1.26
    hour
    1.23
    minute
    1.20
    yard
    1.20
    touch
    1.19
    straight
    1.18
    gamer
    1.17
    Act Density 0.049%

    No Known Activations