INDEX
    Explanations

    concepts related to love and relationships

    New Auto-Interp
    Negative Logits
     Shepherd
    -0.17
    ervo
    -0.16
    ennes
    -0.14
    icher
    -0.14
    ullan
    -0.14
    omik
    -0.14
    itution
    -0.14
     gren
    -0.14
    ypad
    -0.13
     Mezi
    -0.13
    POSITIVE LOGITS
     pat
    0.31
     kin
    0.25
     mat
    0.24
     паÑĤ
    0.23
     nuclear
    0.21
     Kin
    0.21
     Nuclear
    0.21
    pat
    0.21
    Kin
    0.20
     Pat
    0.20
    Act Density 0.045%

    No Known Activations