INDEX
Explanations
punctuation marks and special characters in the text
New Auto-Interp
Negative Logits
ouz
-0.16
PLIT
-0.14
plits
-0.14
Pace
-0.14
caps
-0.14
agini
-0.14
_iters
-0.13
Geile
-0.13
Äħż
-0.13
thôi
-0.13
POSITIVE LOGITS
ì§Ħ
0.15
PTH
0.15
883
0.15
chine
0.14
اض
0.14
Olymp
0.14
umer
0.14
493
0.14
çī
0.13
Mull
0.13
Activations Density 0.007%