INDEX
    Explanations

    geometric shapes

    New Auto-Interp
    Negative Logits
     frig
    -0.08
     supervised
    -0.08
     lwm
    -0.08
     (+
    -0.07
     massive
    -0.07
     JAN
    -0.07
     сервер
    -0.07
     turb
    -0.07
    -0.07
    ACL
    -0.07
    POSITIVE LOGITS
    _cube
    0.08
    _note
    0.08
    0.08
    .Note
    0.08
    -note
    0.08
     Note
    0.08
     Xmas
    0.08
    0.08
     Traveling
    0.07
    .She
    0.07
    Act Density 0.008%

    No Known Activations