INDEX
    Explanations

    references to beauty and skincare products

    New Auto-Interp
    Negative Logits
     Sür
    -0.16
    OrNil
    -0.15
    ãĤµãĤ¤
    -0.14
    .isSuccess
    -0.14
    γά
    -0.14
     Traff
    -0.14
     saf
    -0.14
    ãģ£ãģ
    -0.14
    erp
    -0.14
    prite
    -0.14
    POSITIVE LOGITS
     serum
    0.31
     Serum
    0.28
     cream
    0.23
     facial
    0.23
     face
    0.22
     Treatment
    0.22
     mask
    0.22
     Facial
    0.22
     treatment
    0.21
     hydr
    0.20
    Act Density 0.063%

    No Known Activations