INDEX
    Explanations

    mentions of user interface components or widgets

    New Auto-Interp
    Negative Logits
    OGND
    -0.70
     Maury
    -0.56
     كومونز
    -0.55
     medy
    -0.54
     Strecken
    -0.54
    chr
    -0.52
    how
    -0.51
     nonUne
    -0.51
    Jum
    -0.51
    msgTypes
    -0.50
    POSITIVE LOGITS
    widget
    1.99
     widget
    1.53
    Widget
    1.46
     Widget
    1.42
     createState
    1.34
    widgets
    1.32
     widgets
    1.31
     Widgets
    1.21
    setupUi
    1.20
    WebControls
    1.17
    Act Density 0.013%

    No Known Activations