INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     rayas
    1.04
     чор
    1.01
     olyan
    1.01
     سیاه
    1.01
     พวก
    0.96
    слова
    0.96
     яв
    0.95
    astes
    0.95
     zák
    0.95
     suprem
    0.94
    POSITIVE LOGITS
     computer
    1.54
     Computer
    1.43
     Engine
    1.42
     electronics
    1.40
     computers
    1.39
     engine
    1.37
     Computers
    1.31
     machinery
    1.25
     PC
    1.24
     Electronics
    1.22
    Act Density 0.310%

    No Known Activations