INDEX
Explanations
sentences starting with the pronoun "I"
New Auto-Interp
Negative Logits
ẫn
-0.17
igne
-0.17
ercul
-0.15
ÙĪØ²Ùĩ
-0.14
//~
-0.14
azor
-0.14
suy
-0.14
vier
-0.14
erguson
-0.13
istributed
-0.13
POSITIVE LOGITS
personally
0.20
myself
0.15
guar
0.15
Personally
0.15
estate
0.14
.fits
0.14
795
0.14
ë¶
0.13
еÑģÑĤв
0.13
HS
0.13
Activations Density 0.150%