INDEX
    Explanations

    circle radii calculations

    New Auto-Interp
    Negative Logits
    fruit
    -0.08
     guru
    -0.08
    /project
    -0.08
    特色
    -0.08
    Guru
    -0.08
    -width
    -0.08
    shine
    -0.08
    _hosts
    -0.07
     humild
    -0.07
    ightly
    -0.07
    POSITIVE LOGITS
     acos
    0.09
     grieving
    0.08
     Cure
    0.08
     Clip
    0.08
     mwy
    0.08
     deutschen
    0.08
    დინარე
    0.08
     toirt
    0.08
     drowning
    0.08
     computes
    0.08
    Act Density 0.015%

    No Known Activations