INDEX
    Explanations

    occupations and roles related to various professions

    New Auto-Interp
    Negative Logits
    erland
    -0.15
    erb
    -0.14
     Sutton
    -0.14
    asu
    -0.14
    anga
    -0.14
    ondere
    -0.13
    dek
    -0.13
    cion
    -0.13
    .geo
    -0.13
     conc
    -0.13
    POSITIVE LOGITS
    Ïģιά
    0.15
    -turned
    0.15
    toMatch
    0.15
    ijn
    0.14
    \web
    0.14
    _ln
    0.14
    itten
    0.14
    otle
    0.14
    .usermodel
    0.14
    stown
    0.14
    Act Density 0.143%

    No Known Activations