INDEX
    Explanations

    phrases related to romantic relationships and the dynamics of love

    New Auto-Interp
    Negative Logits
    ihan
    -0.16
    rank
    -0.15
     Separator
    -0.14
    SED
    -0.14
    unused
    -0.14
    çĶ
    -0.14
    Ñħов
    -0.14
    PLICIT
    -0.14
    olson
    -0.13
    ennie
    -0.13
    POSITIVE LOGITS
     someone
    0.20
     partner
    0.19
     commitment
    0.19
     Prince
    0.18
     permanent
    0.18
    amment
    0.18
     Someone
    0.17
    Someone
    0.17
    hta
    0.17
     soul
    0.16
    Act Density 0.136%

    No Known Activations