INDEX
    Explanations

    identifiers and numerical attributes related to individuals and groups

    New Auto-Interp
    Negative Logits
     mate
    -0.15
     Král
    -0.14
    ache
    -0.14
    Ñĸп
    -0.14
    mate
    -0.14
    sher
    -0.14
    opal
    -0.14
    âĦ¢
    -0.14
     Donate
    -0.14
    unsch
    -0.13
    POSITIVE LOGITS
    人çī©
    0.17
    awl
    0.17
    emoc
    0.15
     günü
    0.14
     persons
    0.14
    orang
    0.14
     ÙĬÙĪÙħ
    0.14
    umd
    0.14
    ORA
    0.14
    åij¼
    0.14
    Act Density 0.016%

    No Known Activations