INDEX
    Explanations

    statements and opinions about social issues and justice

    New Auto-Interp
    Negative Logits
    iven
    -0.16
    fy
    -0.16
    ibble
    -0.15
    zano
    -0.15
    ستÙĩ
    -0.15
    295
    -0.14
    /favicon
    -0.14
    hill
    -0.14
    fmt
    -0.14
    Bang
    -0.14
    POSITIVE LOGITS
     ÑĪÑĤÑĥ
    0.16
     Jeb
    0.15
    ëŀĢ
    0.15
    lated
    0.14
    oscope
    0.14
    /=
    0.14
     cheap
    0.14
    alles
    0.14
     sexy
    0.14
    roi
    0.14
    Act Density 0.248%

    No Known Activations