INDEX
    Explanations

    numbers and percentages

    New Auto-Interp
    Negative Logits
     contraste
    0.39
    🍆
    0.38
    owal
    0.38
     Tutak
    0.38
    他說
    0.38
    steuerung
    0.38
     dilig
    0.37
    ന്തപു
    0.37
     Schauspiel
    0.37
     townships
    0.37
    POSITIVE LOGITS
     CH
    0.40
     three
    0.40
     rolled
    0.38
    CH
    0.37
     TRI
    0.37
     не
    0.36
     mandatory
    0.36
     bac
    0.36
     remaining
    0.36
     rolling
    0.35
    Act Density 0.028%

    No Known Activations