INDEX
Explanations
names of individuals, possibly in the context of government or politics
forms of proper nouns and specific names related to individuals or entities
New Auto-Interp
Negative Logits
equivalent
-0.67
litter
-0.66
EDITION
-0.64
trad
-0.64
envy
-0.62
Âł
-0.61
local
-0.61
AAA
-0.61
magnification
-0.60
quad
-0.60
POSITIVE LOGITS
ovich
1.21
ansky
1.20
zynski
1.20
owsky
1.14
inski
1.14
kowski
1.13
ovsky
1.12
baugh
1.10
owicz
1.10
heimer
1.10
Activations Density 0.236%