INDEX
    Explanations

    professional/academic texts

    New Auto-Interp
    Negative Logits
     Scotts
    -0.67
     Scott
    -0.64
     NSCoder
    -0.64
     himo
    -0.64
     kasarigan
    -0.63
    ReusableCell
    -0.60
    transQ
    -0.59
     Saffron
    -0.58
    PreferredItem
    -0.58
     DbSet
    -0.58
    POSITIVE LOGITS
    abancı
    0.52
     giustizia
    0.47
    alnız
    0.45
    мені
    0.45
    новниш
    0.45
    0.45
     frem
    0.43
     terceira
    0.42
     brancas
    0.41
     старости
    0.40
    Act Density 0.008%

    No Known Activations