INDEX
Explanations
mentions of historical events and figures
New Auto-Interp
Negative Logits
.community
-0.17
instein
-0.14
Wagner
-0.14
Nome
-0.14
Ballard
-0.14
iom
-0.14
Vog
-0.14
Victorian
-0.14
ray
-0.13
::-
-0.13
POSITIVE LOGITS
177
0.34
Found
0.33
178
0.31
Benjamin
0.29
Declaration
0.29
Revolutionary
0.28
Jefferson
0.28
founding
0.27
colonies
0.27
Found
0.27
Activations Density 0.130%