INDEX
    Explanations

    sentences related to social commentary or critiques of society

    New Auto-Interp
    Negative Logits
    onal
    -0.16
     Broad
    -0.16
    earch
    -0.15
     Randall
    -0.15
     broad
    -0.15
     Grü
    -0.14
     GenerationType
    -0.14
     Colum
    -0.14
    acer
    -0.14
    Broad
    -0.13
    POSITIVE LOGITS
    REP
    0.16
    971
    0.15
    672
    0.15
    istrovstvÃŃ
    0.14
    orz
    0.14
    cker
    0.14
    quez
    0.14
    472
    0.14
    /inet
    0.13
    ÐŁÐļ
    0.13
    Act Density 0.551%

    No Known Activations