INDEX
    Explanations

    expressions of love and affection

    New Auto-Interp
    Negative Logits
     myſelf
    -0.72
     Inſ
    -0.72
     Biôgrafia
    -0.71
     betweenstory
    -0.68
     iſt
    -0.68
     iconFacebook
    -0.68
     Miquel
    -0.67
    Datuak
    -0.67
    usermodel
    -0.66
    PMailer
    -0.66
    POSITIVE LOGITS
     Love
    1.13
    Love
    1.10
    love
    0.87
     LOVE
    0.86
     love
    0.77
    LOVE
    0.77
     Like
    0.74
     powder
    0.67
     Luke
    0.65
     Josh
    0.65
    Act Density 0.076%

    No Known Activations