INDEX
    Explanations

    sentence fragments/questions

    New Auto-Interp
    Negative Logits
    oredCriteria
    -0.80
    -0.71
     autorytatywna
    -0.66
     propOrder
    -0.57
     op
    -0.53
    )}>
    -0.52
    HasBeenSet
    -0.51
    }}">
    -0.48
    ).
    -0.48
    Autoritní
    -0.47
    POSITIVE LOGITS
     itſelf
    1.02
    ſelf
    0.94
     Efq
    0.93
     themſelves
    0.92
    neſs
    0.89
     iſt
    0.88
     ་་
    0.87
     myſelf
    0.85
    ſelves
    0.84
    VersionUID
    0.84
    Act Density 2.787%

    No Known Activations