INDEX
    Explanations

    references to royal titles or announcements involving royalty

    New Auto-Interp
    Negative Logits
    eki
    -0.15
     We
    -0.14
     Voll
    -0.14
     hyp
    -0.14
    helper
    -0.14
    471
    -0.14
    UBL
    -0.13
    olit
    -0.13
    udos
    -0.13
    íĸ¥
    -0.13
    POSITIVE LOGITS
     His
    0.60
    His
    0.50
     Her
    0.42
     Ðķго
    0.39
     HR
    0.35
    Her
    0.34
     HM
    0.33
    HR
    0.32
     HH
    0.32
     HIS
    0.32
    Act Density 0.133%

    No Known Activations