INDEX
Explanations
references to Christopher Columbus and discussions of his legacy
New Auto-Interp
Negative Logits
Hakk
-0.16
obao
-0.15
anga
-0.14
udden
-0.14
(Gravity
-0.14
aliz
-0.14
ода
-0.14
Rolling
-0.14
oui
-0.14
fsm
-0.14
POSITIVE LOGITS
Rounded
0.17
descon
0.16
Discovery
0.16
mapping
0.16
maps
0.16
discovery
0.16
Discover
0.15
rounded
0.15
Mapping
0.15
Discovery
0.15
Activations Density 0.054%