INDEX
Explanations
names of groups of people ending in 'ians'
references to people from various nationalities or regions
New Auto-Interp
Negative Logits
shown
-0.72
ilts
-0.69
UCK
-0.69
URES
-0.69
URE
-0.68
aped
-0.67
ASED
-0.67
srfAttach
-0.66
ISTER
-0.66
ntil
-0.66
POSITIVE LOGITS
ians
1.41
hip
1.00
ervatives
0.90
apolis
0.86
opolis
0.81
hips
0.80
awei
0.78
aurus
0.77
rejoice
0.76
ync
0.75
Activations Density 0.012%