INDEX
Explanations
references to human rights issues and social justice concerns
New Auto-Interp
Negative Logits
Users
-0.21
Participants
-0.19
_USERS
-0.19
Users
-0.18
Players
-0.18
-users
-0.18
users
-0.17
_users
-0.17
Persons
-0.17
Customers
-0.17
POSITIVE LOGITS
entire
0.26
whole
0.22
elected
0.20
stores
0.20
innocent
0.19
tens
0.18
places
0.18
cities
0.18
shops
0.18
Whole
0.17
Activations Density 0.333%