INDEX
    Explanations

    emerging topics related to social, economic, and environmental issues

    New Auto-Interp
    Negative Logits
    .
    -0.14
    èĢĮ
    -0.13
    .;
    -0.13
    _are
    -0.13
    .↵
    -0.13
     whereas
    -0.13
    ught
    -0.13
    ceeded
    -0.12
    Are
    -0.12
    .;↵
    -0.12
    POSITIVE LOGITS
     that
    0.31
     chosen
    0.31
     underlying
    0.29
     they
    0.28
     behind
    0.28
     itself
    0.28
     responsible
    0.26
     accompanying
    0.26
     themselves
    0.25
     we
    0.24
    Act Density 0.400%

    No Known Activations