INDEX
Explanations
occurrences of the word "Fu" and its variations, indicating a focus on certain key terms or names
New Auto-Interp
Negative Logits
enting
-0.07
otts
-0.06
iff
-0.06
disin
-0.06
ately
-0.06
innie
-0.06
de
-0.06
athing
-0.06
iams
-0.06
ita
-0.06
POSITIVE LOGITS
elling
0.09
elled
0.09
ersh
0.08
ungi
0.08
elp
0.08
led
0.08
å°Ķ
0.08
vyh
0.07
rown
0.07
.lp
0.07
Activations Density 0.005%