INDEX
Explanations
quoted speech or dialogue
New Auto-Interp
Negative Logits
ogi
-0.17
ophon
-0.15
unning
-0.14
Uncategorized
-0.14
etections
-0.14
_REF
-0.14
Gül
-0.14
IGO
-0.13
etch
-0.13
otes
-0.13
POSITIVE LOGITS
s
0.20
KF
0.15
ripe
0.14
-lfs
0.14
verm
0.14
anda
0.13
alth
0.13
sar
0.13
arro
0.13
Pil
0.13
Activations Density 0.041%