INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Sphere
    -0.10
     Sandwich
    -0.09
    .xyz
    -0.09
    loo
    -0.09
     Leon
    -0.09
    Sphere
    -0.09
    753
    -0.09
     ï¼ŀ
    -0.08
    .POS
    -0.08
    buzz
    -0.08
    POSITIVE LOGITS
     width
    0.18
     Width
    0.13
    .width
    0.13
    \twidth
    0.12
    Width
    0.12
    width
    0.12
    (width
    0.11
     GLsizei
    0.11
    _width
    0.11
    .Width
    0.11
    Act Density 0.047%

    No Known Activations