INDEX
Explanations
proper nouns, particularly names of people and places
New Auto-Interp
Negative Logits
by
-0.18
stown
-0.17
ville
-0.15
esco
-0.15
__(
-0.14
__
-0.14
eko
-0.14
oko
-0.13
hone
-0.13
361
-0.13
POSITIVE LOGITS
(@
0.17
+offset
0.15
contributing
0.14
|
0.14
Contrib
0.14
contri
0.14
¦¬
0.14
Posts
0.14
|:
0.14
Photos
0.14
Activations Density 0.058%