INDEX
    Explanations

    mentions of "ball," particularly in various contexts such as sports or physical objects

    New Auto-Interp
    Negative Logits
    -0.63
     Myra
    -0.62
    CES
    -0.60
     Cesar
    -0.58
     Muster
    -0.58
    pto
    -0.58
    ipto
    -0.58
    yeni
    -0.57
     Guil
    -0.57
    Guil
    -0.57
    POSITIVE LOGITS
     balls
    1.59
     ball
    1.57
     BALL
    1.55
     Ball
    1.53
     Balls
    1.52
    ball
    1.44
    Balls
    1.43
    Ball
    1.42
    BALL
    1.40
    balls
    1.29
    Act Density 0.113%

    No Known Activations