INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    InputBorder
    -0.59
    RectangleBorder
    -0.53
    AxisAlignment
    -0.52
    LEGGI
    -0.50
    DockStyle
    -0.50
     degeneracy
    -0.49
     dévelo
    -0.48
     kasarigan
    -0.48
    kheim
    -0.47
    étoit
    -0.47
    POSITIVE LOGITS
     "
    2.38
     ("
    1.48
     -"
    1.34
     :"
    1.34
    -"
    1.31
    ("
    1.23
     "...
    1.22
     ,"
    1.22
    :"
    1.21
    "
    1.20
    Act Density 0.170%

    No Known Activations