INDEX
Explanations
phrases related to specific groups of people, particularly with the term "People" emphasized
mentions of "People" in various contexts, particularly related to political or social topics
New Auto-Interp
Negative Logits
èª
-0.83
Lank
-0.82
NES
-0.71
Emer
-0.70
etr
-0.70
TEXTURE
-0.69
ITAL
-0.67
SPONSORED
-0.67
ECD
-0.67
lain
-0.67
POSITIVE LOGITS
folk
0.94
people
0.92
smugglers
0.90
People
0.84
oples
0.78
aganda
0.77
wills
0.77
wana
0.76
lihood
0.76
ciating
0.75
Activations Density 0.010%