INDEX
Explanations
references to political leaders and their relationships with others
New Auto-Interp
Negative Logits
erais
-0.15
Detail
-0.15
ÑĤÑĶ
-0.15
ilst
-0.15
vi
-0.15
arguments
-0.14
spor
-0.14
-addon
-0.14
à¥įरम
-0.14
Mention
-0.13
POSITIVE LOGITS
observation
0.26
pozor
0.26
observed
0.24
dry
0.24
obs
0.24
observing
0.24
observe
0.23
observations
0.23
Observ
0.22
tart
0.22
Activations Density 0.247%