INDEX
Explanations
words related to leadership or positions of authority
words associated with presidential roles and duties
New Auto-Interp
Negative Logits
yip
-0.69
inately
-0.69
irlf
-0.68
hler
-0.68
stro
-0.68
sexes
-0.67
ycle
-0.66
drm
-0.66
zsche
-0.65
usercontent
-0.65
POSITIVE LOGITS
esses
0.73
enment
0.70
çİĭ
0.70
IAL
0.69
VER
0.68
SHIP
0.68
Shen
0.68
ctuary
0.67
士
0.67
ctory
0.67
Activations Density 0.129%