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

    Neuronpedia

    INDEX
    Explanations

    activities and games, especially ones involving interaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arella
    -0.15
    ñana
    -0.14
    olist
    -0.14
    webdriver
    -0.14
    burgh
    -0.13
    ÑĢеÑħ
    -0.13
    phan
    -0.13
    ç¥Ń
    -0.13
    avigator
    -0.13
    179
    -0.13
    POSITIVE LOGITS
     dice
    0.35
     cards
    0.32
     chess
    0.31
     card
    0.29
     tic
    0.27
     Tic
    0.27
     poker
    0.27
     game
    0.27
     games
    0.27
     Cards
    0.26
    Act Density 0.287%

    No Known Activations