INDEX
    Explanations

    topics related to infidelity and romantic relationships

    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.79
     Efq
    -0.74
     itſelf
    -0.72
     myſelf
    -0.70
    ſelf
    -0.69
     auffi
    -0.67
    )':
    -0.66
     ſy
    -0.65
     ]
    
    -0.65
     ―――――
    -0.64
    POSITIVE LOGITS
    :✨
    0.66
     courting
    0.52
     dating
    0.51
     marriage
    0.51
     marry
    0.51
     Tinder
    0.49
     amores
    0.49
    對象
    0.48
     married
    0.48
     romance
    0.48
    Act Density 0.189%

    No Known Activations