INDEX
Explanations
sentences ending with punctuation marks
New Auto-Interp
Negative Logits
otas
-0.15
angu
-0.14
mers
-0.14
atin
-0.14
оÑĤов
-0.14
ÎŃ
-0.14
lay
-0.14
moth
-0.14
åīį
-0.13
INU
-0.13
POSITIVE LOGITS
è¡
0.15
idos
0.14
atform
0.14
خاÙĨ
0.14
idas
0.14
imore
0.14
apore
0.14
uffy
0.14
.ide
0.13
æ¯
0.13
Activations Density 0.032%