INDEX
Explanations
references to authors and their works in children's literature
New Auto-Interp
Negative Logits
itez
-0.16
ioni
-0.15
िà¤
-0.14
Matth
-0.14
ITTLE
-0.14
encil
-0.14
unu
-0.14
Cristina
-0.14
iska
-0.14
Commentary
-0.14
POSITIVE LOGITS
-NLS
0.17
tip
0.15
auer
0.14
pix
0.14
taraf
0.14
еÑģÑı
0.13
LEY
0.13
@author
0.13
زر
0.13
251
0.13
Activations Density 0.222%