INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    |--------------------------------------------------------------------------↵
    -0.07
    -0.06
     presidential
    -0.06
    _bal
    -0.06
     zákon
    -0.06
    death
    -0.06
     convolution
    -0.06
     Wyoming
    -0.06
    ansom
    -0.06
     TEXT
    -0.06
    POSITIVE LOGITS
     série
    0.07
     named
    0.06
     στις
    0.06
    builtin
    0.06
     elected
    0.06
     dut
    0.06
    实施
    0.06
    Ο
    0.06
     cumpl
    0.06
    rou
    0.06
    Act Density 0.016%

    No Known Activations