INDEX
Explanations
numerical values and mathematical references
New Auto-Interp
Negative Logits
izard
-0.17
udeau
-0.15
.volley
-0.15
uzzi
-0.15
RIA
-0.14
ngle
-0.14
Thrones
-0.14
usi
-0.14
ammen
-0.14
RedirectTo
-0.14
POSITIVE LOGITS
Hub
0.18
oola
0.16
hub
0.16
Hub
0.15
Girlfriend
0.15
.ct
0.15
hub
0.15
agh
0.14
lander
0.14
sol
0.14
Activations Density 0.209%