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

    Neuronpedia

    INDEX
    Explanations

    words related to games

    oai_token-act-pair · gpt-3.5-turbo

    references to games or gamification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Osw
    -0.74
    attery
    -0.72
    hips
    -0.66
    ayers
    -0.63
    inx
    -0.61
    atts
    -0.60
     Apostles
    -0.60
    verty
    -0.60
     Lanka
    -0.59
     Tub
    -0.59
    POSITIVE LOGITS
    plan
    1.05
    manship
    1.02
     theoret
    0.98
    play
    0.96
    keepers
    0.96
    wright
    0.95
    keeper
    0.95
    plays
    0.94
     chang
    0.93
    PLAY
    0.90
    Act Density 0.060%

    No Known Activations