INDEX
    Explanations

    references to emotions and personal connections in intimate relationships

    New Auto-Interp
    Negative Logits
    hiba
    -0.18
    aska
    -0.16
    ж
    -0.15
    _literal
    -0.15
    .rawValue
    -0.14
    rible
    -0.14
    liste
    -0.14
    733
    -0.14
    ewn
    -0.14
    aksi
    -0.13
    POSITIVE LOGITS
    umbo
    0.14
     Cruc
    0.14
     mixin
    0.14
    ,/
    0.14
     è½
    0.13
    emon
    0.13
    -r
    0.13
    craft
    0.13
     Pis
    0.13
     Dere
    0.13
    Act Density 0.154%

    No Known Activations