INDEX
    Explanations

    well succeeded, well used, well learned

    New Auto-Interp
    Negative Logits
     not
    -0.90
     even
    -0.77
    pthread
    -0.75
    Basil
    -0.75
    ish
    -0.73
    ʲ
    -0.72
    otypic
    -0.72
     historia
    -0.72
     Sergio
    -0.72
     freund
    -0.71
    POSITIVE LOGITS
    veillance
    1.28
    heure
    0.98
     墓
    0.95
     خاصی
    0.91
     буенча
    0.91
     Beschluss
    0.90
     peggio
    0.88
     LXX
    0.87
     puțin
    0.85
    0.84
    Act Density 0.007%

    No Known Activations