INDEX
    Explanations

    expressions of uncertainty, desire, and reflection

    New Auto-Interp
    Negative Logits
    ulemon
    -0.56
     Westen
    -0.48
    falgar
    -0.44
    про
    -0.43
    érience
    -0.42
    Angleterre
    -0.41
    зера
    -0.41
     Sahib
    -0.40
     Zephyr
    -0.39
     [{
    
    -0.39
    POSITIVE LOGITS
     Efq
    0.90
     hoped
    0.89
     بيها
    0.83
     Theſe
    0.82
     Beſ
    0.74
     wanted
    0.73
     incomplète
    0.72
     purpoſe
    0.72
    RectangleBorder
    0.72
     mergeFrom
    0.68
    Act Density 0.218%

    No Known Activations