INDEX
    Explanations

    explosives and explosions

    New Auto-Interp
    Negative Logits
     आराम
    0.79
     Drought
    0.72
    0.71
     Singers
    0.71
    0.71
    сор
    0.70
    moda
    0.68
    holomorphic
    0.68
     Rowling
    0.66
     Dracula
    0.66
    POSITIVE LOGITS
     explosives
    1.20
     explosive
    1.12
     explosions
    1.09
     explode
    1.07
     deton
    1.06
     explodes
    1.05
    爆炸
    1.02
     detonations
    1.02
     fireworks
    1.02
    1.02
    Act Density 0.094%

    No Known Activations