INDEX
    Explanations

    words related to relationships and partnerships

    mentions of couples and their relationships

    New Auto-Interp
    Negative Logits
    é¾
    -0.87
    ukong
    -0.81
     Flavoring
    -0.74
    OLOG
    -0.74
    Downloadha
    -0.65
     Kov
    -0.64
    osure
    -0.63
    ibaba
    -0.63
    OUGH
    -0.62
    shire
    -0.62
    POSITIVE LOGITS
     couples
    1.03
    folk
    0.89
    riages
    0.84
    ples
    0.83
    iliated
    0.81
    maid
    0.80
    hood
    0.79
    nesday
    0.75
    tones
    0.74
    icles
    0.71
    Act Density 0.024%

    No Known Activations