INDEX
    Explanations

    promotional language related to discounts and sales

    New Auto-Interp
    Negative Logits
    illet
    -0.18
    ieri
    -0.18
    ouro
    -0.18
    asher
    -0.17
    nev
    -0.15
    olist
    -0.15
    ittle
    -0.15
    annah
    -0.15
    ovah
    -0.14
    awaiter
    -0.14
    POSITIVE LOGITS
    790
    0.15
    AVA
    0.14
    AVOR
    0.14
    rama
    0.14
     subsidi
    0.14
    tual
    0.14
    CanBe
    0.14
     tuto
    0.14
     Stocks
    0.13
     Toro
    0.13
    Act Density 0.016%

    No Known Activations