INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    verwijspagina
    -0.78
    RuleContext
    -0.77
     igång
    -0.76
    portál
    -0.73
     säll
    -0.66
    warnai
    -0.63
    håll
    -0.63
     skolan
    -0.63
     vägen
    -0.62
     amitié
    -0.62
    POSITIVE LOGITS
     bera
    0.42
     Blak
    0.42
     crossorigin
    0.40
    #![
    0.39
    AnimationsModule
    0.38
     butterknife
    0.37
     overs
    0.36
    intur
    0.35
     tuck
    0.35
     Stra
    0.35
    Act Density 0.007%

    No Known Activations