INDEX
    Explanations

    relationships/couples

    New Auto-Interp
    Negative Logits
     husband
    -0.09
     familiale
    -0.08
    Bright
    -0.08
     csal
    -0.08
    family
    -0.08
     family
    -0.08
     cheese
    -0.08
    .Owner
    -0.08
     خاندان
    -0.08
     خانواده
    -0.08
    POSITIVE LOGITS
     tomography
    0.08
     contrib
    0.08
     өндір
    0.08
     J
    0.08
     nir
    0.08
     kantite
    0.08
    .todos
    0.08
     гум
    0.08
    _J
    0.08
    	J
    0.08
    Act Density 0.044%

    No Known Activations