INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    -comment
    -0.08
    .comment
    -0.08
     comentario
    -0.08
     tungsten
    -0.08
    .counter
    -0.07
    BMW
    -0.07
     Berkeley
    -0.07
     слово
    -0.07
     comentar
    -0.07
     nové
    -0.07
    POSITIVE LOGITS
     storefront
    0.09
    店舗
    0.08
    Brick
    0.08
     Retail
    0.08
     Eternal
    0.08
     brains
    0.08
     Brick
    0.08
    indak
    0.08
     업체
    0.08
    0.08
    Act Density 0.003%

    No Known Activations