INDEX
Explanations
historically
phrases that explicitly frame something in historical context or refer to long-term origins and continuity
New Auto-Interp
Negative Logits
quals
-0.08
duer
-0.08
ไม
-0.07
μη
-0.07
cuello
-0.07
Hotels
-0.07
�
-0.07
MENT
-0.07
तर
-0.07
採
-0.07
POSITIVE LOGITS
以来
0.13
history
0.09
историю
0.09
(history
0.08
.history
0.08
істор
0.08
cardiovascular
0.08
-standing
0.08
年以来
0.08
બા
0.08
Activations Density 0.037%