INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Zus
    0.47
     RESEARCH
    0.43
     bib
    0.43
     drunkenness
    0.42
     biblical
    0.42
     printable
    0.42
     disgusted
    0.41
     Druck
    0.40
     auch
    0.39
     Increasingly
    0.39
    POSITIVE LOGITS
    namely
    0.41
    ']));
    0.41
    templat
    0.40
    ])));
    0.39
     выде
    0.38
    '));
    0.37
    ']])
    0.37
     مرحبا
    0.37
     BlueprintName
    0.36
    ];//
    0.36
    Act Density 0.001%

    No Known Activations