INDEX
    Explanations

    mentions of political affiliations and actions in the context of Senate proceedings

    New Auto-Interp
    Negative Logits
     Sloan
    -0.15
     imbalance
    -0.15
    ooks
    -0.14
    atican
    -0.14
    lassen
    -0.14
    -pos
    -0.14
    rush
    -0.14
    aign
    -0.13
    ibraltar
    -0.13
    łģ
    -0.13
    POSITIVE LOGITS
    modifiable
    0.14
    @student
    0.14
    ิà¸ļ
    0.14
    istrovstvÃŃ
    0.14
    بس
    0.14
    jection
    0.14
    tridges
    0.14
     пÑĢим
    0.14
    -Sah
    0.13
    ØŃÙĦ
    0.13
    Act Density 0.023%

    No Known Activations