INDEX
    Explanations

    references to smoking and related behaviors

    New Auto-Interp
    Negative Logits
     Washer
    -0.16
    öz
    -0.15
    iê
    -0.14
    |#
    -0.14
     æ¢
    -0.14
    gem
    -0.14
    ibir
    -0.14
     Oman
    -0.14
    utr
    -0.14
    andex
    -0.13
    POSITIVE LOGITS
     tobacco
    0.73
     smoking
    0.72
     cigarette
    0.67
     smokers
    0.65
     cigarettes
    0.65
     smoker
    0.64
     Tobacco
    0.64
     Smoking
    0.64
     smoke
    0.63
     nicotine
    0.60
    Act Density 0.155%

    No Known Activations