INDEX
Explanations
instances of the word "been."
New Auto-Interp
Negative Logits
leo
-0.15
åĨµ
-0.15
defgroup
-0.14
enberg
-0.14
룬ìĬ¤
-0.14
Düz
-0.14
pard
-0.14
íį¼
-0.14
ÑĤен
-0.14
addtogroup
-0.14
POSITIVE LOGITS
fucking
0.19
fuck
0.18
fucked
0.18
ibel
0.17
oria
0.16
metal
0.16
fucks
0.15
Fuck
0.15
Naz
0.15
cons
0.15
Activations Density 0.000%