INDEX
Explanations
specific dates and significant keywords associated with historical events
New Auto-Interp
Negative Logits
lately
-0.22
tonight
-0.21
recently
-0.19
currently
-0.18
recent
-0.18
recent
-0.17
later
-0.17
today
-0.17
now
-0.17
tomorrow
-0.16
POSITIVE LOGITS
began
0.17
份
0.15
ä¼´
0.15
adays
0.15
came
0.14
aday
0.14
éłĥ
0.14
kea
0.14
годÑĥ
0.14
became
0.13
Activations Density 0.128%