INDEX
    Explanations

    mentions of clothing items and online shopping promotions

    New Auto-Interp
    Negative Logits
    undry
    -0.15
     Cout
    -0.14
    ovic
    -0.14
    672
    -0.14
    :animated
    -0.14
    ุล
    -0.14
    bole
    -0.14
    udio
    -0.14
     Gross
    -0.13
     Amend
    -0.13
    POSITIVE LOGITS
     beri
    0.16
    erli
    0.15
    orget
    0.14
    ,No
    0.14
     &
    0.14
    è¾°
    0.14
    ilha
    0.14
    aised
    0.14
    Borders
    0.13
     Battlefield
    0.13
    Act Density 0.383%

    No Known Activations