INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     stunned
    -0.08
     plats
    -0.07
    $lang
    -0.07
     complied
    -0.07
     Lie
    -0.07
     konsek
    -0.07
     stake
    -0.07
    Attach
    -0.07
     attach
    -0.07
     Sto
    -0.07
    POSITIVE LOGITS
     مضبوط
    0.09
    ுள்ளதாக
    0.09
    īj
    0.09
     كث
    0.08
    ’ing
    0.08
     poo
    0.08
     whakah
    0.08
    (bits
    0.08
     Pork
    0.08
     aye
    0.08
    Act Density 0.011%

    No Known Activations