INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    ValueStyle
    -1.09
    NewUrlParser
    -0.84
     Normdatei
    -0.73
    BeforeMethod
    -0.69
     GenerationType
    -0.67
    ScopeManager
    -0.67
    ANTLR
    -0.67
     beginnetje
    -0.67
    клопе
    -0.67
     MenuView
    -0.66
    POSITIVE LOGITS
     shirts
    0.58
     hoodies
    0.58
    iseta
    0.57
     sweatshirt
    0.57
     sweatshirts
    0.56
     camisetas
    0.54
     slogans
    0.53
     hoodie
    0.52
    hirts
    0.52
     manif
    0.52
    Act Density 0.066%

    No Known Activations