INDEX
    Explanations

    non-specific categories

    New Auto-Interp
    Negative Logits
     زیرمه
    0.76
    विण्यासाठी
    0.66
     وړیا
    0.65
    建築
    0.64
    0.64
    utilisateur
    0.63
    尺寸
    0.63
    记得
    0.63
    Pumpkin
    0.62
     прият
    0.62
    POSITIVE LOGITS
     other
    0.73
     category
    0.73
     misuse
    0.72
     inconclusive
    0.72
     non
    0.70
    除了
    0.70
     selain
    0.70
     irrelevant
    0.69
     kategori
    0.69
     besides
    0.68
    Act Density 0.313%

    No Known Activations