INDEX
Explanations
phrases related to historical events occurring in the 19th century
historical dates, particularly in the 18th and 19th centuries
New Auto-Interp
Negative Logits
orter
-0.74
ickers
-0.73
ical
-0.69
ete
-0.69
ointed
-0.69
iques
-0.69
itional
-0.69
adata
-0.68
ovie
-0.67
ique
-0.67
POSITIVE LOGITS
650
1.09
58
0.91
91
0.91
92
0.90
94
0.89
th
0.88
85
0.87
87
0.86
71
0.85
mph
0.85
Activations Density 0.045%