INDEX
    Explanations

    mentions of fashion and fashion-related events or items

    New Auto-Interp
    Negative Logits
    canestro
    -0.43
    writeFieldEnd
    -0.42
     EconPapers
    -0.42
     perfección
    -0.42
     bénévoles
    -0.41
     Manfaat
    -0.40
     disambiguazione
    -0.40
    ウンサー
    -0.39
    Fcn
    -0.39
     judiciales
    -0.39
    POSITIVE LOGITS
     designer
    0.67
    designer
    0.64
     fashion
    0.64
     designers
    0.63
    fashion
    0.60
    figer
    0.58
    Fashion
    0.58
     Fashion
    0.58
     Designer
    0.57
    Designer
    0.57
    Act Density 0.075%

    No Known Activations