INDEX
    Explanations

    pronouns and possessive forms that indicate a personal connection or relationship

    New Auto-Interp
    Negative Logits
    CADE
    -0.17
    yt
    -0.14
    iv
    -0.14
     McConnell
    -0.14
    fos
    -0.14
    _TYPED
    -0.14
    jian
    -0.14
     зал
    -0.14
    offers
    -0.14
    dao
    -0.13
    POSITIVE LOGITS
    EDGE
    0.15
    reff
    0.14
     ведÑĮ
    0.14
    หลวà¸ĩ
    0.13
    ilet
    0.13
    uffers
    0.13
    /mobile
    0.13
    лев
    0.13
    ismus
    0.13
    abar
    0.13
    Act Density 0.097%

    No Known Activations