INDEX
Explanations
repeated negations or expressions of denial
New Auto-Interp
Negative Logits
}\
-0.69
ceci
-0.66
Portail
-0.65
suivantes
-0.63
culturelles
-0.63
IONI
-0.61
laquelle
-0.61
*/
-0.60
Mek
-0.60
Населення
-0.60
POSITIVE LOGITS
no
1.77
No
1.73
No
1.61
NO
1.57
no
1.31
NO
1.29
Noyes
1.14
sno
1.08
nof
1.08
noOf
1.03
Activations Density 0.161%