INDEX
    Explanations

    expressions of personal relationships and social connections

    New Auto-Interp
    Negative Logits
    åij³
    -0.14
     tastes
    -0.14
     taste
    -0.14
     initially
    -0.14
    esco
    -0.14
    RowIndex
    -0.13
    ãĤŃãĥ³ãĤ°
    -0.13
    ÉĻ
    -0.13
    blas
    -0.13
    deaux
    -0.13
    POSITIVE LOGITS
     recent
    0.33
    recent
    0.29
     recently
    0.28
     lately
    0.26
     previous
    0.25
     Recent
    0.23
    Recent
    0.21
    _recent
    0.21
     давно
    0.20
     previously
    0.19
    Act Density 0.337%

    No Known Activations