INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     purpoſe
    -0.84
     ſmall
    -0.80
    TagMode
    -0.73
     Reſ
    -0.73
     katun
    -0.72
     Anſ
    -0.71
     ſche
    -0.70
     system
    -0.70
     ſy
    -0.70
     perſon
    -0.70
    POSITIVE LOGITS
     of
    0.65
     referenties
    0.56
    Джерела
    0.53
     in
    0.48
     from
    0.47
     genoeg
    0.45
    ,
    0.45
    InjectAttribute
    0.43
     as
    0.43
    Weblinks
    0.43
    Act Density 0.084%

    No Known Activations