INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    댓글
    -0.09
     busiest
    -0.09
     hamburg
    -0.08
     댓글
    -0.08
     النات
    -0.08
     groundwater
    -0.08
     gratifying
    -0.08
     plut
    -0.08
     rej
    -0.08
     SPC
    -0.08
    POSITIVE LOGITS
     embroidered
    0.10
     embroidery
    0.09
    _flat
    0.08
    HEMA
    0.08
     garment
    0.08
     কাপ
    0.08
    -flat
    0.08
     плать
    0.07
     neckline
    0.07
     sleeves
    0.07
    Act Density 0.039%

    No Known Activations