INDEX
    Explanations

    possessive pronouns and other related personal references

    New Auto-Interp
    Negative Logits
    åĬĽ
    -0.16
    inci
    -0.16
     arch
    -0.15
     system
    -0.15
    aco
    -0.15
     center
    -0.15
    241
    -0.15
     race
    -0.14
     cent
    -0.14
    per
    -0.14
    POSITIVE LOGITS
    ouden
    0.16
    .scal
    0.15
    ESCO
    0.15
    hoa
    0.15
    ÄįÃŃ
    0.15
    opup
    0.14
     Kenny
    0.14
    код
    0.14
     kys
    0.14
    kowski
    0.14
    Act Density 0.166%

    No Known Activations