INDEX
    Explanations

    Morphemes/word structure

    New Auto-Interp
    Negative Logits
    (app
    -0.07
    2
    -0.07
    af
    -0.07
     of
    -0.07
    _polygon
    -0.07
    _guess
    -0.07
     Employ
    -0.07
    uffling
    -0.07
     (
    -0.07
    ncpy
    -0.07
    POSITIVE LOGITS
    0.10
     ndaj
    0.10
    Attached
    0.10
     attached
    0.09
    attached
    0.09
     Zubehör
    0.09
     appended
    0.09
     suffix
    0.09
     attaching
    0.09
     attachments
    0.09
    Act Density 0.003%

    No Known Activations