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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "game."

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific sport or game, particularly in the context of player performance and strategy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xon
    -0.75
    sie
    -0.72
    CLASSIFIED
    -0.68
    CAST
    -0.68
    orescent
    -0.66
    hai
    -0.61
    ãģ¦
    -0.61
    ikers
    -0.61
    aii
    -0.60
    RIC
    -0.60
    POSITIVE LOGITS
    plan
    0.92
    keeper
    0.88
    play
    0.86
    wright
    0.83
    PLAY
    0.83
    keepers
    0.82
    fighter
    0.82
    arium
    0.81
    plays
    0.81
    manship
    0.78
    Act Density 0.049%

    No Known Activations