INDEX
    Explanations

    content related to destruction and significant historical events

    New Auto-Interp
    Negative Logits
    mons
    -0.16
     homophobic
    -0.15
     Klo
    -0.15
    TickCount
    -0.14
    .scalablytyped
    -0.14
     Dump
    -0.14
    aley
    -0.14
     saldo
    -0.14
     provid
    -0.13
    rella
    -0.13
    POSITIVE LOGITS
     idol
    0.27
     Idol
    0.25
     pag
    0.23
     pagan
    0.20
     apost
    0.20
     sin
    0.20
     idols
    0.19
     poll
    0.19
     devil
    0.18
     pollution
    0.18
    Act Density 0.217%

    No Known Activations