INDEX
    Explanations

    references to lips and related cosmetics

    New Auto-Interp
    Negative Logits
    etten
    -0.18
    etro
    -0.15
    ogan
    -0.15
    istrovstvÃŃ
    -0.15
    ayar
    -0.15
    alles
    -0.14
     Hindered
    -0.14
    orts
    -0.14
     Beste
    -0.14
     imperson
    -0.14
    POSITIVE LOGITS
    ixo
    0.15
    avin
    0.15
     kiss
    0.14
     Plenty
    0.14
     kissing
    0.14
    adelphia
    0.14
    ologna
    0.14
    หลวà¸ĩ
    0.13
    ause
    0.13
    uhl
    0.13
    Act Density 0.007%

    No Known Activations