INDEX
    Explanations

    phrases expressing opinion or sentiment

    expressions of public opinion or sentiments on various topics

    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.04
    2:0.14
    3:0.05
    4:0.07
    5:0.08
    6:0.04
    7:0.05
    8:0.08
    9:0.23
    10:0.09
    11:0.03
    Negative Logits
     Smithsonian
    -1.26
     Edition
    -1.17
     Tycoon
    -1.14
    zona
    -1.12
    thia
    -1.08
    bill
    -1.04
     Cases
    -1.03
     contrace
    -1.03
    Contribut
    -1.02
     Columb
    -1.02
    POSITIVE LOGITS
     sentiment
    1.33
     resonate
    1.27
    isSpecialOrderable
    1.24
     populism
    1.20
     slogans
    1.17
    below
    1.15
     contag
    1.12
    establishment
    1.11
    pmwiki
    1.07
     popul
    1.07
    Act Density 0.004%

    No Known Activations