INDEX
    Explanations

    expressions related to trends and current popularity

    New Auto-Interp
    Negative Logits
    eka
    -0.15
    anton
    -0.15
    alle
    -0.15
    utters
    -0.14
     mastur
    -0.14
    linkplain
    -0.14
    LOPT
    -0.14
    ozem
    -0.14
    EDIA
    -0.13
     dynam
    -0.13
    POSITIVE LOGITS
     fashion
    0.63
    -fashion
    0.54
     Fashion
    0.52
     fashionable
    0.50
    Fashion
    0.44
     moda
    0.44
    ashion
    0.42
     trendy
    0.39
     trend
    0.37
     Vogue
    0.34
    Act Density 0.129%

    No Known Activations