INDEX
    Explanations

    names and identifiers, particularly those that resemble user names or technical terms

    New Auto-Interp
    Negative Logits
    RectangleBorder
    -0.81
    ISupport
    -0.76
    Traceback
    -0.72
    awtextra
    -0.71
    subpackage
    -0.69
    esModule
    -0.68
    tvguidetime
    -0.66
    Personendaten
    -0.65
    KommentareTeilen
    -0.65
    ruptedException
    -0.64
    POSITIVE LOGITS
    em
    0.59
    ki
    0.55
    irk
    0.53
    ker
    0.52
    night
    0.52
    kkkk
    0.52
    ids
    0.52
     duk
    0.51
     sauvages
    0.50
     tsk
    0.50
    Act Density 0.259%

    No Known Activations