INDEX
    Explanations

    expressions and references related to romance and romantic themes

    New Auto-Interp
    Negative Logits
     Kraj
    -0.16
    anda
    -0.16
    irut
    -0.15
    -bodied
    -0.15
     åζ
    -0.14
    houses
    -0.14
    виÑĩай
    -0.14
    998
    -0.14
    iam
    -0.14
    manship
    -0.14
    POSITIVE LOGITS
    agne
    0.17
     Ventura
    0.15
     Marketable
    0.15
    entic
    0.14
    ques
    0.14
    kowski
    0.14
     Bas
    0.14
    Ïįν
    0.13
    ENTS
    0.13
    isiert
    0.13
    Act Density 0.019%

    No Known Activations