INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    CloseOperation
    -0.45
     dezelve
    -0.44
     pouvoit
    -0.43
    stylers
    -0.42
     Majefty
    -0.42
    berdayakan
    -0.41
     Juifs
    -0.41
     ſind
    -0.40
    ThemeProvider
    -0.39
     automatiques
    -0.39
    POSITIVE LOGITS
     fabric
    1.30
     FABRIC
    1.27
     Fabric
    1.26
    Fabric
    1.23
    fabric
    1.20
    Fab
    1.05
    FABRIC
    1.04
     fab
    1.02
     Fab
    1.00
    fab
    0.96
    Act Density 0.059%

    No Known Activations