INDEX
    Explanations

    the presence of the phrase "Game" or related references to games and their contexts

    New Auto-Interp
    Negative Logits
    erre
    -0.14
    enor
    -0.14
    ãģŀ
    -0.13
     SPD
    -0.13
     planta
    -0.13
    ibur
    -0.13
    ei
    -0.13
    ornado
    -0.13
    leurs
    -0.13
    ivicrm
    -0.13
    POSITIVE LOGITS
     games
    0.67
    games
    0.54
     Games
    0.52
    Games
    0.49
     game
    0.46
    _games
    0.41
    .games
    0.39
     Game
    0.35
    game
    0.33
    -game
    0.33
    Act Density 0.001%

    No Known Activations