INDEX
Explanations
prominent political figures and their roles or characteristics in historical contexts
New Auto-Interp
Negative Logits
addCriterion
-0.18
ableView
-0.14
ink
-0.14
awn
-0.14
ei
-0.14
èĪį
-0.14
ystone
-0.14
Globe
-0.13
бав
-0.13
retire
-0.13
POSITIVE LOGITS
Jong
0.21
-Un
0.20
Il
0.19
Un
0.19
Uns
0.18
-il
0.17
-un
0.16
Workers
0.16
ãĤ¦ãĥ³
0.16
Un
0.15
Activations Density 0.005%