INDEX
    Explanations

    possessive pronouns and expressions of ownership or affiliation

    New Auto-Interp
    Negative Logits
    ubber
    -0.15
    UCE
    -0.14
    оÑĤÑĢеб
    -0.14
    Ñģом
    -0.14
    aney
    -0.14
    own
    -0.13
    iday
    -0.13
    olet
    -0.13
    æĭĵ
    -0.13
     èį
    -0.13
    POSITIVE LOGITS
     Bast
    0.16
    erva
    0.16
    orr
    0.14
    inkel
    0.14
    Ãł
    0.14
     astr
    0.13
     Adler
    0.13
    Britain
    0.13
    uml
    0.13
    jit
    0.13
    Act Density 0.163%

    No Known Activations