INDEX
    Explanations

    the word "so", especially when followed by "it" and "was"

    New Auto-Interp
    Negative Logits
    AnchorStyles
    -0.59
    ribut
    -0.56
     arri
    -0.48
     sommes
    -0.48
     eigentlich
    -0.48
    naire
    -0.47
     arrivo
    -0.46
     want
    -0.46
     Chwiliwch
    -0.45
     volont
    -0.45
    POSITIVE LOGITS
    ArgsConstructor
    0.85
     näin
    0.80
     архивлан
    0.73
    providedIn
    0.71
     Methuen
    0.71
     Shakspeare
    0.71
     TestBed
    0.69
     Paglinawan
    0.69
     Roskov
    0.68
    Così
    0.68
    Act Density 0.019%

    No Known Activations