INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     grze
    -0.68
    addCriterion
    -0.67
    Aiheesta
    -0.66
    Personensuche
    -0.65
     relève
    -0.65
     atlik
    -0.62
    agissait
    -0.62
     loisirs
    -0.61
    __":
    -0.61
     Zeke
    -0.60
    POSITIVE LOGITS
     window
    3.23
     windows
    3.05
     Window
    2.84
    window
    2.69
     WINDOW
    2.55
    windows
    2.37
    Window
    2.36
     Fenster
    2.24
    fenster
    2.15
    WINDOW
    2.12
    Act Density 0.056%

    No Known Activations