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

    Neuronpedia

    INDEX
    Explanations

    the word "game" with varying contexts and associations

    oai_token-act-pair · gpt-3.5-turbo

    references to games or game mechanics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ayers
    -0.80
    ancies
    -0.76
    thens
    -0.67
    æĢ
    -0.67
    çīĪ
    -0.66
    inx
    -0.65
    iffe
    -0.63
    atts
    -0.63
    obook
    -0.61
     claimant
    -0.61
    POSITIVE LOGITS
    manship
    1.07
    keepers
    1.01
    play
    1.00
    keeper
    0.96
    cock
    0.94
    cube
    0.90
    wright
    0.90
    pad
    0.90
    plan
    0.87
    cloth
    0.85
    Act Density 0.067%

    No Known Activations