INDEX
    Explanations

    mentions of Hillary Clinton

    New Auto-Interp
    Negative Logits
    677
    -0.16
    ulo
    -0.15
    annt
    -0.15
    mund
    -0.15
    aghan
    -0.15
    utdown
    -0.14
    £i
    -0.14
    leston
    -0.14
    amil
    -0.13
    indrome
    -0.13
    POSITIVE LOGITS
    undry
    0.17
    asics
    0.16
    WN
    0.15
    andler
    0.15
     numer
    0.14
    wil
    0.14
    legg
    0.14
    annon
    0.14
    YPE
    0.14
     Yol
    0.14
    Act Density 0.005%

    No Known Activations