INDEX
    Explanations

    mentions of Barack Obama and his administration

    New Auto-Interp
    Negative Logits
    CESS
    -0.18
    ings
    -0.15
     Woodward
    -0.14
     du
    -0.14
    829
    -0.14
    æ³ķ人
    -0.14
    ÎŃÏĤ
    -0.14
     deterministic
    -0.13
    indsay
    -0.13
    ikt
    -0.13
    POSITIVE LOGITS
    -era
    0.17
     lẽ
    0.16
     Barack
    0.15
    orc
    0.14
    ollider
    0.14
     Obama
    0.14
    eurs
    0.14
     lúc
    0.14
     moder
    0.13
     depreci
    0.13
    Act Density 0.019%

    No Known Activations