INDEX
    Explanations

    romantic partners and relationships

    New Auto-Interp
    Negative Logits
    Mrs
    0.90
    parency
    0.78
    ząd
    0.69
     Mrs
    0.69
    ganos
    0.68
     மிக்க
    0.68
    undra
    0.67
     करिकुलम
    0.66
    Modify
    0.64
    Wis
    0.64
    POSITIVE LOGITS
     romantic
    2.47
     romance
    2.27
     boyfriend
    2.02
     Romantic
    2.02
     romances
    2.01
     dating
    1.98
     romant
    1.97
    Romantic
    1.90
    romantic
    1.85
     роман
    1.84
    Act Density 0.178%

    No Known Activations