INDEX
Explanations
instances of dialogue or speech
New Auto-Interp
Negative Logits
åĽ
-0.18
oria
-0.16
399
-0.15
497
-0.14
ammen
-0.13
.localized
-0.13
ushi
-0.13
åĿª
-0.13
phones
-0.13
cul
-0.13
POSITIVE LOGITS
umer
0.18
bilin
0.16
EQ
0.15
eÄį
0.14
.git
0.14
ittal
0.14
itel
0.13
·»
0.13
"default
0.13
alist
0.13
Activations Density 0.002%