INDEX
    Explanations

    details related to physical objects and their characteristics

    New Auto-Interp
    Negative Logits
    inning
    -0.16
    ãĥ¼ãĤº
    -0.15
    _CAST
    -0.15
     Ell
    -0.14
    ago
    -0.14
    ensch
    -0.14
    á¿Ĩ
    -0.14
     casts
    -0.14
    Cast
    -0.13
     sculpt
    -0.13
    POSITIVE LOGITS
     paper
    0.19
    纸
    0.19
     Paper
    0.19
    .gdx
    0.17
     Pages
    0.17
    -paper
    0.17
     pages
    0.17
    /cards
    0.17
     printing
    0.17
     Tear
    0.16
    Act Density 0.042%

    No Known Activations