INDEX
Explanations
occurrences of the article "a" and its variations
New Auto-Interp
Negative Logits
pson
-0.16
olu
-0.16
allen
-0.15
azen
-0.15
uess
-0.14
egen
-0.14
Leod
-0.14
usi
-0.14
zel
-0.14
atee
-0.14
POSITIVE LOGITS
éϵ
0.19
ahoma
0.16
oud
0.15
Mint
0.15
phabet
0.15
dition
0.14
ummer
0.14
ampp
0.14
imuth
0.14
tek
0.14
Activations Density 0.073%