INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     nationale
    0.22
     হাসপাত
    0.22
     عالی
    0.21
     dearest
    0.21
     algumas
    0.21
    Uma
    0.21
    adine
    0.21
     melhores
    0.21
     perfeita
    0.21
     regno
    0.21
    POSITIVE LOGITS
     Vulcan
    0.23
     Collectors
    0.22
     -----------
    0.22
     Voltage
    0.21
     Cloth
    0.21
    εργ
    0.20
     Chorus
    0.20
     jäl
    0.20
     Вер
    0.20
     Interested
    0.20
    Act Density 0.001%

    No Known Activations