INDEX
    Explanations

    expressions of enthusiasm and admiration towards creative works or artistic projects

    New Auto-Interp
    Negative Logits
    illos
    -0.15
    ÑģÑĤÑĢов
    -0.15
     Král
    -0.14
    .epam
    -0.14
     huy
    -0.14
     kvinna
    -0.14
     xuyên
    -0.14
    ovsky
    -0.14
    rophy
    -0.14
     Genç
    -0.13
    POSITIVE LOGITS
     deb
    0.15
     orient
    0.15
     Tone
    0.14
    CT
    0.14
    çīĩ
    0.14
     Alliance
    0.14
     Carn
    0.14
    T
    0.14
     wed
    0.13
    ffd
    0.13
    Act Density 0.037%

    No Known Activations