INDEX
    Explanations

    references to snack and fast food items, particularly those high in sugar and fat

    New Auto-Interp
    Negative Logits
     الحره
    -0.53
     Cowley
    -0.49
     motore
    -0.48
     Deane
    -0.47
     ilg
    -0.47
     Dil
    -0.44
     Kearns
    -0.42
     Lindgren
    -0.42
    EMI
    -0.41
    ropia
    -0.41
    POSITIVE LOGITS
     snack
    1.40
     snacks
    1.35
     Snack
    1.29
     popcorn
    1.23
     chips
    1.21
    Snack
    1.19
     Snacks
    1.16
     Chips
    1.16
     fries
    1.15
    Snacks
    1.13
    Act Density 0.134%

    No Known Activations