INDEX
    Explanations

    references to political movements and candidates

    New Auto-Interp
    Negative Logits
    ptal
    -0.15
    tplib
    -0.15
    ìĹ´
    -0.15
    isay
    -0.15
    ago
    -0.14
    seys
    -0.14
    егÑĢа
    -0.14
     zav
    -0.14
    Oi
    -0.14
    ắn
    -0.14
    POSITIVE LOGITS
     Redistribution
    0.16
     Sweep
    0.15
    ationToken
    0.14
    лед
    0.14
    ÑĢиг
    0.14
     beating
    0.13
    ære
    0.13
     cos
    0.13
    raki
    0.13
    422
    0.13
    Act Density 0.008%

    No Known Activations