INDEX
Explanations
mentions of specific dates and times in the text
New Auto-Interp
Negative Logits
leh
-0.17
/cop
-0.16
recent
-0.15
hait
-0.14
Registrar
-0.14
Ere
-0.14
aspers
-0.14
onn
-0.14
imoto
-0.14
979
-0.13
POSITIVE LOGITS
next
0.35
next
0.29
(next
0.27
Next
0.26
NEXT
0.26
-next
0.25
.next
0.25
,next
0.24
_next
0.24
_NEXT
0.23
Activations Density 0.035%