INDEX
    Explanations

    programming/technical text

    New Auto-Interp
    Negative Logits
    DockStyle
    -1.10
     AssemblyCulture
    -0.94
    ArgsConstructor
    -0.92
     Audiodateien
    -0.85
    CloseOperation
    -0.81
     EconPapers
    -0.80
    Билгалдахарш
    -0.79
     Theſe
    -0.79
    MemoryWarning
    -0.78
    InSection
    -0.77
    POSITIVE LOGITS
    <bos>
    1.05
    .
    0.87
     (
    0.56
    ,
    0.51
    l
    0.50
    r
    0.49
    (
    0.46
    ;
    0.45
    G
    0.43
    as
    0.42
    Act Density 0.003%

    No Known Activations