INDEX
    Explanations

    specific brands and product names

    New Auto-Interp
    Negative Logits
    IsContent
    -1.01
     propOrder
    -0.96
    -0.90
    ReusableCell
    -0.90
    sizeCache
    -0.86
    PreferredItem
    -0.82
    AddTagHelper
    -0.82
     ویکی‌پدی
    -0.81
    DockStyle
    -0.80
     snippetHide
    -0.80
    POSITIVE LOGITS
     solchen
    0.48
    past
    0.48
    หมด
    0.46
    0.46
    gy
    0.45
     past
    0.43
    intra
    0.43
    0.42
     débat
    0.42
    /"+
    0.42
    Act Density 1.786%

    No Known Activations