INDEX
    Explanations

    references to personal pronouns and possessive adjectives

    New Auto-Interp
    Negative Logits
    kil
    -0.17
    ono
    -0.14
     Retail
    -0.14
    ele
    -0.14
    оÑĢаз
    -0.14
    esser
    -0.14
    erna
    -0.14
    åĤ¬
    -0.14
    fr
    -0.13
    ава
    -0.13
    POSITIVE LOGITS
    .scalablytyped
    0.17
    .TextAlignment
    0.15
     visit
    0.15
    _INCLUDED
    0.15
    OMPI
    0.14
     å¯Į
    0.14
    íij¸
    0.14
    iba
    0.14
    .ManyToManyField
    0.14
    ird
    0.14
    Act Density 0.078%

    No Known Activations