INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    -0.56
    <eos>
    -0.55
    ValueStyle
    -0.54
    </em>
    -0.52
     […]
    -0.49
     createState
    -0.46
    -0.46
    MigrationBuilder
    -0.44
     podjela
    -0.43
     sobra
    -0.43
    POSITIVE LOGITS
    :\/\/
    0.84
     iſt
    0.78
     للمعارف
    0.74
    InputBorder
    0.71
     Monfieur
    0.70
     Jefus
    0.70
     pleaſure
    0.69
    chowa
    0.69
     تضيفلها
    0.69
     متعلقه
    0.69
    Act Density 0.115%

    No Known Activations