INDEX
    Explanations

    smoking and smoke policies

    New Auto-Interp
    Negative Logits
     inscriptions
    0.50
     जेसीबी
    0.47
     वर्ण
    0.44
     registr
    0.42
    0.42
    innerHTML
    0.41
     مدرس
    0.40
     उछ
    0.39
     JSON
    0.39
    ெழு
    0.38
    POSITIVE LOGITS
     smoking
    2.08
     Smoking
    1.99
    Smoking
    1.99
     smoker
    1.95
     smokers
    1.93
     cigarette
    1.90
     smoke
    1.85
     Smoke
    1.79
     cigarettes
    1.77
    smoking
    1.77
    Act Density 0.006%

    No Known Activations