INDEX
Explanations
instances of the pronoun "I."
New Auto-Interp
Negative Logits
fak
-0.17
sæ
-0.16
erne
-0.16
zon
-0.15
zad
-0.15
persön
-0.14
swore
-0.14
InvalidOperationException
-0.14
μμα
-0.14
̧
-0.13
POSITIVE LOGITS
hast
0.19
suppose
0.19
guess
0.17
sup
0.16
batis
0.16
gather
0.15
eline
0.15
isel
0.15
Guess
0.14
Guess
0.14
Activations Density 0.071%