INDEX
Explanations
references to social constructs and relationships in historical contexts
New Auto-Interp
Negative Logits
opers
-0.15
Coffee
-0.14
rb
-0.14
dc
-0.14
qli
-0.13
ally
-0.13
agna
-0.13
αÏĤ
-0.13
ÃŃa
-0.13
uels
-0.13
POSITIVE LOGITS
ayi
0.15
ìĦ¸
0.14
à¹Ģà¸Ĭ
0.13
ori
0.13
ÑĤÑĢи
0.13
presence
0.13
rent
0.13
osi
0.13
cen
0.13
953
0.12
Activations Density 0.268%