INDEX
    Explanations

    statements and discussions about political positions and policies related to social issues

    New Auto-Interp
    Negative Logits
     Roose
    -0.15
    ipeg
    -0.14
    OSC
    -0.14
    à¤Ŀ
    -0.13
     Roosevelt
    -0.13
    ÑĢог
    -0.13
    ĵåIJį
    -0.13
    bÄĽ
    -0.13
    _mux
    -0.13
     gren
    -0.13
    POSITIVE LOGITS
    hta
    0.18
    ãĤ¤ãĥ«
    0.15
    iture
    0.15
    Aligned
    0.15
     беÑĤ
    0.14
     sop
    0.14
    herits
    0.14
    aye
    0.13
    arel
    0.13
    ukkan
    0.13
    Act Density 0.126%

    No Known Activations