INDEX
Explanations
occurrences of the letter 'F' in various contexts
New Auto-Interp
Negative Logits
lops
-0.19
lop
-0.17
iber
-0.17
loor
-0.17
aille
-0.17
actor
-0.16
lash
-0.16
loat
-0.16
acial
-0.16
riends
-0.16
POSITIVE LOGITS
ichten
0.19
och
0.17
ettes
0.17
itchen
0.16
forest
0.16
fest
0.15
eni
0.15
ium
0.15
enn
0.15
oug
0.15
Activations Density 0.033%