INDEX
    Explanations

    references to romantic events and relationships

    New Auto-Interp
    Negative Logits
     >=",
    -0.84
     שוליים
    -0.69
    ConstraintMaker
    -0.64
     bénévoles
    -0.59
    setVerticalGroup
    -0.59
    Itoa
    -0.58
     المعرف
    -0.58
    providedIn
    -0.57
     amitié
    -0.57
     مشين
    -0.57
    POSITIVE LOGITS
     romantic
    1.34
    romantic
    1.13
     romance
    1.09
     Romantic
    1.06
    Romantic
    1.01
     Valentine
    0.99
     romántica
    0.90
     romantique
    0.89
     romantis
    0.89
     romanti
    0.87
    Act Density 0.133%

    No Known Activations