INDEX
    Explanations

    except for lists of items

    New Auto-Interp
    Negative Logits
     all
    0.72
     allemaal
    0.68
     overall
    0.63
     все
    0.61
     Overall
    0.61
    overall
    0.59
     всё
    0.57
     altogether
    0.56
     ofta
    0.55
     كله
    0.54
    POSITIVE LOGITS
     except
    1.16
     kecuali
    1.05
     excepto
    1.02
    except
    1.00
     EXCEPT
    0.89
     imaginable
    0.89
     sauf
    0.88
     Except
    0.83
    Except
    0.81
     excepting
    0.80
    Act Density 0.082%

    No Known Activations