INDEX
    Explanations

    phrases indicating academic or institutional affiliations

    New Auto-Interp
    Negative Logits
     dol
    -0.42
     مقد
    -0.42
     scre
    -0.41
     Svar
    -0.40
     ...
    -0.38
    <eos>
    -0.38
    Sector
    -0.36
     Sozial
    -0.35
     Ø
    -0.35
     ('
    -0.35
    POSITIVE LOGITS
     College
    0.94
    College
    0.85
     COLLEGE
    0.82
    college
    0.80
     college
    0.78
    COLLEGE
    0.74
    sizeCache
    0.71
    OGND
    0.70
     colleges
    0.68
     Colleges
    0.68
    Act Density 0.005%

    No Known Activations