INDEX
Explanations
quotations within texts
occurrences of quotes and related metadata in text
New Auto-Interp
Negative Logits
agos
-0.83
aucas
-0.74
oulos
-0.70
hop
-0.70
lips
-0.68
rams
-0.67
Rohing
-0.66
ult
-0.66
collar
-0.66
surrog
-0.65
POSITIVE LOGITS
Originally
1.03
Quote
0.88
Quote
0.78
Posted
0.77
Edited
0.73
·
0.70
Reply
0.69
Developer
0.68
Investigator
0.68
Hi
0.67
Activations Density 0.045%