INDEX
    Explanations

    punctuation

    New Auto-Interp
    Negative Logits
    akata
    -0.08
     DAR
    -0.08
     rigu
    -0.08
    wera
    -0.07
     shar
    -0.07
     qor
    -0.07
    yari
    -0.07
     niya
    -0.07
     tern
    -0.07
     aute
    -0.07
    POSITIVE LOGITS
     Pequ
    0.09
    Ο
    0.08
     Trader
    0.08
    Stan
    0.07
    329
    0.07
    0.07
     رفع
    0.07
    يف
    0.07
    xyz
    0.07
    0.07
    Act Density 0.046%

    No Known Activations