INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     propOrder
    -0.90
     CreateTagHelper
    -0.88
    onoi
    -0.88
     forskj
    -0.86
     voorbeeld
    -0.86
    (''),
    -0.83
     digitais
    -0.83
    ,:]
    -0.82
    LayoutPanel
    -0.82
    complexContent
    -0.82
    POSITIVE LOGITS
    <bos>
    2.41
    '
    0.82
    0.75
    2
    0.71
    an
    0.68
    1
    0.66
    3
    0.66
    o
    0.64
    7
    0.62
     to
    0.61
    Act Density 1.285%

    No Known Activations