INDEX
    Explanations

    mentions of Alexandra Ocasio-Cortez and related political references

    New Auto-Interp
    Negative Logits
    imo
    -0.16
     ingest
    -0.15
    jen
    -0.15
    156
    -0.14
    lan
    -0.14
    afka
    -0.14
    ohl
    -0.14
    rome
    -0.14
    By
    -0.14
     By
    -0.14
    POSITIVE LOGITS
    abela
    0.14
    adiator
    0.14
    GetProperty
    0.14
    enderit
    0.14
    orro
    0.14
     gord
    0.14
    ायद
    0.13
    izyon
    0.13
    usters
    0.13
    adius
    0.13
    Act Density 0.006%

    No Known Activations