INDEX
    Explanations

    references to online communities and their guidelines

    New Auto-Interp
    Negative Logits
    __':
    -0.56
     Zeller
    -0.51
    formik
    -0.50
    __":
    
    -0.46
    RegressionTest
    -0.45
    TagHelper
    -0.44
    ciach
    -0.44
    __':
    
    -0.43
    edes
    -0.43
    vants
    -0.42
    POSITIVE LOGITS
     DeviantArt
    0.82
     Vikipedi
    0.80
    Portale
    0.78
     fhew
    0.70
     youtuber
    0.69
    saraba
    0.68
     MySpace
    0.68
     wattpad
    0.68
    bukkit
    0.67
    حياته
    0.66
    Act Density 0.506%

    No Known Activations