INDEX
Explanations
dates and their occurrences in the text
New Auto-Interp
Negative Logits
umbn
-0.16
ovice
-0.16
_svc
-0.15
Łèĥ½
-0.15
eful
-0.14
estro
-0.14
antha
-0.14
icture
-0.14
CADE
-0.14
uve
-0.14
POSITIVE LOGITS
396
0.17
482
0.17
T
0.15
0.14
bes
0.14
ello
0.14
ÑĤ
0.13
globally
0.13
10
0.13
13
0.13
Activations Density 0.027%