INDEX
Explanations
the letter 'f' in various contexts
New Auto-Interp
Negative Logits
ÄĽt
-0.17
oti
-0.17
alance
-0.16
ت
-0.15
YA
-0.15
áºŃt
-0.15
eliac
-0.15
ajor
-0.15
r
-0.14
errat
-0.14
POSITIVE LOGITS
aked
0.20
asta
0.20
aket
0.18
omat
0.18
akes
0.18
ails
0.18
ailable
0.18
aken
0.18
ailing
0.18
etched
0.17
Activations Density 0.029%