INDEX
    Explanations

    mathematical statements

    New Auto-Interp
    Negative Logits
    -0.09
     altru
    -0.09
     moyo
    -0.09
    -0.09
     тщательно
    -0.08
     agricultural
    -0.08
     victime
    -0.08
     ❤️
    -0.08
    -0.08
     Communist
    -0.08
    POSITIVE LOGITS
     perpendicular
    0.10
    二维
    0.10
    pendicular
    0.10
     planar
    0.09
     coax
    0.09
     intersections
    0.09
     intersection
    0.08
    Intersect
    0.08
    _plane
    0.08
     plane
    0.08
    Act Density 0.015%

    No Known Activations