INDEX
    Explanations

    terms related to articles, documents, or academic references

    New Auto-Interp
    Negative Logits
    ,
    -0.91
    .
    -0.89
     and
    -0.86
    -
    -0.81
    -0.79
     in
    -0.77
    1
    -0.74
     to
    -0.73
     on
    -0.73
    <eos>
    -0.70
    POSITIVE LOGITS
     يتيمه
    1.70
    ^(@)
    1.58
     ſind
    1.41
     ―――――
    1.38
     iſt
    1.37
    ")));
    
    1.35
     ་་
    1.34
     autorytatywna
    1.31
    Personensuche
    1.26
    bibfield
    1.25
    Act Density 0.017%

    No Known Activations