INDEX
    Explanations

    references to fashion and clothing, particularly regarding prices and patterns

    New Auto-Interp
    Negative Logits
     للمعارف
    -0.74
    protoimpl
    -0.72
     ProtoMessage
    -0.68
    łem
    -0.63
    extAlignment
    -0.62
    principalColumn
    -0.62
    ครับ
    -0.61
    تقاوى
    -0.57
    ผม
    -0.57
    Diwedd
    -0.56
    POSITIVE LOGITS
     crin
    0.68
     sequin
    0.67
     dolls
    0.65
     sparkly
    0.64
     sequins
    0.64
     Glitter
    0.63
     feminist
    0.63
     scrapbooking
    0.60
     tulle
    0.59
     organza
    0.59
    Act Density 0.617%

    No Known Activations