INDEX
    Explanations

    references to the word "Rub," indicating a focus on variations and usages of this term in different contexts

    New Auto-Interp
    Negative Logits
    ChildScrollView
    -0.68
    StoryboardSegue
    -0.61
    BeginContext
    -0.60
     favoris
    -0.53
     BoxFit
    -0.52
    cerely
    -0.49
    Pref
    -0.49
    DEAR
    -0.46
     Pref
    -0.45
     kaffe
    -0.45
    POSITIVE LOGITS
     Rub
    1.19
     RUB
    1.14
     rub
    1.09
    Rub
    1.08
     rubs
    1.01
     rubbing
    0.98
    RUB
    0.97
    rub
    0.97
     rubbed
    0.87
     Ruby
    0.80
    Act Density 0.075%

    No Known Activations