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

    Neuronpedia

    INDEX
    Explanations

    expressions related to playing games

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ContentAlignment
    -0.63
     ChromeDriver
    -0.58
    UnifiedTopology
    -0.58
    ánea
    -0.53
    kozá
    -0.53
    âneo
    -0.52
    crever
    -0.50
    rouvez
    -0.50
     Nouvelles
    -0.49
     للمعارف
    -0.49
    POSITIVE LOGITS
     played
    1.73
     playing
    1.67
     play
    1.61
     Playing
    1.59
     games
    1.59
     Played
    1.59
    Playing
    1.59
    Played
    1.58
    played
    1.54
     game
    1.47
    Act Density 0.144%

    No Known Activations