INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     gacchati
    0.48
     домой
    0.48
    Goodbye
    0.45
     Затем
    0.43
     Migrate
    0.42
     partire
    0.42
    Transit
    0.42
     منزل
    0.41
     deceduto
    0.41
    0.40
    POSITIVE LOGITS
     manipulation
    0.41
     manipulative
    0.40
     shocking
    0.37
     unsettling
    0.37
     స్థాయిలో
    0.37
     manipulated
    0.37
     exasper
    0.36
     le
    0.35
     manipulating
    0.35
     troubling
    0.35
    Act Density 0.012%

    No Known Activations