INDEX
    Explanations

    mentions of the social media platform Instagram

    New Auto-Interp
    Negative Logits
    Personendaten
    -0.59
     Schluß
    -0.42
    UseVisualStyle
    -0.41
     peluche
    -0.38
     sentado
    -0.37
    contentPane
    -0.36
     Producción
    -0.36
    enumi
    -0.36
    llong
    -0.35
     Bekasi
    -0.34
    POSITIVE LOGITS
     Instagram
    1.21
    Instagram
    1.15
     instagram
    1.02
     INSTAGRAM
    0.99
    instagram
    0.98
    INSTAGRAM
    0.98
     Insta
    0.69
     اینستاگرام
    0.68
     insta
    0.64
    insta
    0.63
    Act Density 0.107%

    No Known Activations