INDEX
    Explanations

    phrases expressing recommendations and buying intentions

    New Auto-Interp
    Negative Logits
    achat
    -0.18
    éné
    -0.16
    velle
    -0.15
    AREST
    -0.15
    arest
    -0.14
    æĩ
    -0.14
    retch
    -0.14
    WARE
    -0.14
     Sick
    -0.14
    ibold
    -0.14
    POSITIVE LOGITS
     myself
    0.15
    뮤
    0.15
     event
    0.14
    ighton
    0.14
     overs
    0.14
     future
    0.14
     Rainbow
    0.13
    οι
    0.13
     cái
    0.13
     stakes
    0.13
    Act Density 0.060%

    No Known Activations