INDEX
    Explanations

    configuration parameters

    New Auto-Interp
    Negative Logits
     if
    -1.80
     most
    -1.64
     as
    -1.64
     while
    -1.63
     before
    -1.51
     just
    -1.48
     some
    -1.45
     five
    -1.41
     after
    -1.41
     another
    -1.39
    POSITIVE LOGITS
     для
    1.41
     venezolano
    1.39
     esetén
    1.38
     possibilité
    1.37
     argentino
    1.36
     alemán
    1.34
     vuonna
    1.33
    では
    1.33
    ぞれ
    1.32
     sorprende
    1.31
    Act Density 0.012%

    No Known Activations