INDEX
    Explanations

    phrases related to terrorism and government actions related to terrorism

    New Auto-Interp
    Negative Logits
    dit
    -0.87
    galitarian
    -0.82
    gling
    -0.70
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.66
     Dolphin
    -0.64
     Volvo
    -0.63
    etch
    -0.62
    ðĿ
    -0.62
    Sync
    -0.61
    BuyableInstoreAndOnline
    -0.61
    POSITIVE LOGITS
    abad
    1.20
     bombings
    0.95
     mastermind
    0.92
     terrorism
    0.89
     terrorists
    0.89
     bombing
    0.88
    ophobic
    0.88
     spree
    0.87
     terrorist
    0.87
     bombers
    0.85
    Act Density 0.045%

    No Known Activations