INDEX
Explanations
the verb "be" in various contexts
New Auto-Interp
Negative Logits
ymb
-0.18
cá
-0.15
rv
-0.15
so
-0.15
ully
-0.14
olean
-0.14
(s
-0.14
-0.14
se
-0.14
ño
-0.13
POSITIVE LOGITS
atform
0.17
plode
0.15
Bund
0.15
pyx
0.15
rieve
0.15
oga
0.15
chalk
0.14
Baghd
0.14
κηÏĤ
0.14
olla
0.13
Activations Density 0.093%