INDEX
    Explanations

    references to the word "Games" in a context related to competitions or entertainment

    New Auto-Interp
    Negative Logits
     politic
    -0.81
    etheless
    -0.68
     acknow
    -0.67
    xious
    -0.67
     unnamed
    -0.67
     compr
    -0.66
    sie
    -0.65
    ract
    -0.65
    uppet
    -0.63
    iosis
    -0.62
    POSITIVE LOGITS
     Games
    1.10
    Games
    1.02
     Flavoring
    0.84
    Beat
    0.81
    Apps
    0.81
     Tournament
    0.81
    Aren
    0.81
     Workshop
    0.78
     Awards
    0.78
     Festival
    0.78
    Act Density 0.007%

    No Known Activations