INDEX
    Explanations

    specific items and concepts related to home and domestic life

    New Auto-Interp
    Negative Logits
    UseVisualStyle
    -0.51
     though
    -0.51
     eux
    -0.51
     I
    -0.49
     attend
    -0.48
     itself
    -0.47
     through
    -0.47
    zarchiwizowane
    -0.45
     in
    -0.45
     zapatillas
    -0.44
    POSITIVE LOGITS
    0.79
     beginnetje
    0.79
    expandindo
    0.78
    rungsseite
    0.77
     disambiguazione
    0.76
    LookAnd
    0.73
    ſelves
    0.72
    0.71
    Personensuche
    0.70
    ſelf
    0.69
    Act Density 0.452%

    No Known Activations