INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     fizz
    -0.10
     mnemonic
    -0.09
     ATM
    -0.09
     Reds
    -0.09
     electrician
    -0.08
     career
    -0.08
     technician
    -0.08
     Technician
    -0.08
    Career
    -0.08
     carrera
    -0.08
    POSITIVE LOGITS
     convex
    0.18
     hull
    0.13
     polygons
    0.13
     shap
    0.12
     polygon
    0.11
    polygon
    0.11
    Polygon
    0.11
    Shape
    0.10
    radius
    0.10
     radius
    0.10
    Act Density 0.022%

    No Known Activations