INDEX
    Explanations

    the name "Hillary Clinton"

    mentions of Hillary Clinton and Bernie Sanders in a political context

    New Auto-Interp
    Negative Logits
    ANK
    -0.88
    ãĥĦ
    -0.78
    ITAL
    -0.72
    ãĥĢ
    -0.70
    Reviewer
    -0.70
     Cy
    -0.70
     Pars
    -0.67
     Flavoring
    -0.67
    ãĥ¯ãĥ³
    -0.65
     Adapt
    -0.65
    POSITIVE LOGITS
    Clinton
    1.01
    abee
    0.88
     Rodham
    0.87
     Clinton
    0.85
     Clintons
    0.83
    eering
    0.82
    clinton
    0.82
    atism
    0.81
    agher
    0.81
    espie
    0.79
    Act Density 0.056%

    No Known Activations