INDEX
    Explanations

    Book, OB, A, Q abbreviations

    New Auto-Interp
    Negative Logits
     over
    -1.33
     created
    -1.25
     all
    -1.22
     them
    -1.16
     where
    -1.14
     needed
    -1.14
     they
    -1.13
     which
    -1.13
     more
    -1.12
     achieve
    -1.12
    POSITIVE LOGITS
     weihnachten
    1.16
    壁纸
    1.12
    zondere
    1.06
    }}/>
    1.05
     noy
    1.03
     listes
    1.02
    1.02
    obviously
    1.02
     AWAY
    1.02
     normalen
    0.98
    Act Density 0.000%

    No Known Activations