INDEX
    Explanations

    references to ancient beliefs, practices, and historical events

    content related to historical or cultural beliefs and practices

    New Auto-Interp
    Negative Logits
     rollout
    -0.78
    IDA
    -0.76
     (@
    -0.76
     Spotlight
    -0.73
    ï¸ı
    -0.73
    hack
    -0.70
     Deadline
    -0.70
    Ryan
    -0.68
    Update
    -0.68
     Emails
    -0.68
    POSITIVE LOGITS
     arist
    0.99
     slaves
    0.95
     clans
    0.94
     peasant
    0.94
     peasants
    0.93
     feudal
    0.93
     primitive
    0.91
     nobles
    0.91
     priests
    0.90
     Ottoman
    0.90
    Act Density 1.376%

    No Known Activations