INDEX
    Explanations

    repeated mentions of the word "event."

    New Auto-Interp
    Negative Logits
    ≦)
    -0.41
    iosi
    -0.40
     './../
    -0.40
    kwij
    -0.39
    lera
    -0.39
    NamedQueries
    -0.39
    lichter
    -0.38
    rungs
    -0.38
     Pinch
    -0.38
    meri
    -0.37
    POSITIVE LOGITS
     event
    1.84
     Event
    1.54
    event
    1.43
     EVENT
    1.42
    Event
    1.38
    EVENT
    1.19
     evento
    1.19
     eventId
    1.03
     Evento
    1.02
     Veranstaltung
    0.94
    Act Density 0.016%

    No Known Activations