INDEX
    Explanations

    occurrences of the word "von" and its variants

    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -1.11
     iſt
    -1.08
    NewUrlParser
    -1.02
     CreateTagHelper
    -0.92
     Reſ
    -0.87
     Lampung
    -0.86
    StructEnd
    -0.85
     HttpNotFound
    -0.85
     weihnachten
    -0.85
     Jefus
    -0.84
    POSITIVE LOGITS
     von
    1.26
     Von
    1.18
    Von
    1.10
    von
    1.06
     mit
    1.02
     VON
    0.89
    VON
    0.71
    woll
    0.68
     wegen
    0.67
     Yoo
    0.65
    Act Density 0.121%

    No Known Activations