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

    Neuronpedia

    INDEX
    Explanations

    phrases related to playing or interacting with a game

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "play" in various forms and contexts, indicating a focus on gaming experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thening
    -0.81
     Beir
    -0.73
     commencement
    -0.69
     pole
    -0.67
    udeau
    -0.63
     Apost
    -0.63
    ewitness
    -0.61
     relocation
    -0.60
    ortium
    -0.60
    ensing
    -0.60
    POSITIVE LOGITS
    tested
    1.22
    testing
    1.16
    ername
    1.09
    testers
    1.03
    test
    1.00
    wright
    0.98
    GROUND
    0.98
    lists
    0.97
     games
    0.92
    tests
    0.87
    Act Density 0.046%

    No Known Activations