INDEX
    Explanations

    names and affiliations related to academic institutions and universities

    New Auto-Interp
    Negative Logits
    merc
    -0.14
     Enc
    -0.14
     twe
    -0.14
    underscore
    -0.14
    ób
    -0.14
    rog
    -0.14
    aling
    -0.13
    екÑĤ
    -0.13
    awa
    -0.13
     Cub
    -0.13
    POSITIVE LOGITS
     Hicks
    0.15
    ÅĦ
    0.15
    845
    0.15
     ><?
    0.14
    imar
    0.14
     soir
    0.14
     Hitch
    0.14
     اÙĦتÙĤ
    0.13
     Jarvis
    0.13
    689
    0.13
    Act Density 0.419%

    No Known Activations