INDEX
Explanations
references to historical documents and dates
New Auto-Interp
Negative Logits
cke
-0.19
later
-0.16
Later
-0.16
phe
-0.16
subsequent
-0.16
icari
-0.15
Enlarge
-0.15
zc
-0.14
Later
-0.14
orz
-0.14
POSITIVE LOGITS
earlier
0.26
previous
0.23
Earlier
0.21
previous
0.21
Earlier
0.20
Previous
0.20
.previous
0.20
Previous
0.19
preceding
0.18
ear
0.18
Activations Density 0.138%