INDEX
Explanations
mentions of the name "Fran" or similar variations
New Auto-Interp
Negative Logits
gaard
-0.17
ence
-0.17
práv
-0.16
andas
-0.15
enha
-0.15
_stdio
-0.15
Consolid
-0.14
Ali
-0.14
tu
-0.14
erdale
-0.13
POSITIVE LOGITS
.TestCase
0.17
ument
0.17
ERY
0.15
utan
0.15
mi
0.15
umerator
0.15
nelle
0.14
Ńå·ŀ
0.14
ãĥ¼ãĥ«
0.14
olia
0.14
Activations Density 0.007%