INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    argout
    -0.62
     الرياضيه
    -0.56
    mybatisplus
    -0.54
     aidé
    -0.52
    eqn
    -0.51
     ajutor
    -0.50
    Figur
    -0.48
    fromnode
    -0.48
     Inici
    -0.48
     picioare
    -0.48
    POSITIVE LOGITS
     aboard
    0.71
     folds
    0.70
     fold
    0.69
     folded
    0.69
     Transparency
    0.67
     Fold
    0.66
     Вікіпе
    0.64
    GenerationType
    0.63
     folding
    0.63
     Francis
    0.63
    Act Density 0.099%

    No Known Activations