INDEX
    Explanations

    specific descriptive attributes related to objects and materials

    New Auto-Interp
    Negative Logits
     esternos
    -0.57
     vítimas
    -0.56
     eşofman
    -0.56
     normalidad
    -0.54
     tė
    -0.52
     hırka
    -0.52
     víctimas
    -0.50
     zimowa
    -0.50
     ocupación
    -0.50
     Privacidade
    -0.49
    POSITIVE LOGITS
    styleUrls
    0.42
     homemade
    0.42
    رشف
    0.41
     gro
    0.41
    testens
    0.40
     plastic
    0.40
     handmade
    0.39
     bur
    0.39
     soft
    0.39
    ForResult
    0.39
    Act Density 0.967%

    No Known Activations