INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    وره
    -0.07
    ipel
    -0.07
    شته
    -0.07
     Hole
    -0.07
    illes
    -0.07
    ACL
    -0.07
     infections
    -0.07
     nine
    -0.06
    وده
    -0.06
     aquel
    -0.06
    POSITIVE LOGITS
     smart
    0.19
     Smart
    0.16
    Smart
    0.15
     SMART
    0.13
    smart
    0.12
     smarter
    0.11
    SMART
    0.10
     smarty
    0.09
    Smarty
    0.08
    _smart
    0.08
    Act Density 0.010%

    No Known Activations