INDEX
    Explanations

    descriptions of entertainers and their performance qualities

    New Auto-Interp
    Negative Logits
    obia
    -0.18
    .ul
    -0.16
    anton
    -0.16
     Gil
    -0.15
    ersist
    -0.15
    ofire
    -0.15
    ouple
    -0.14
    анÑĤа
    -0.14
     gol
    -0.14
    ÑıÑħ
    -0.14
    POSITIVE LOGITS
    chat
    0.16
    æ
    0.15
    chsel
    0.14
    Quaternion
    0.14
     Levin
    0.13
    hem
    0.13
    URITY
    0.13
     Všech
    0.13
    ALK
    0.13
    lex
    0.13
    Act Density 0.097%

    No Known Activations