INDEX
Explanations
keywords related to societal or political issues and controversies
references to societal issues involving fear, conflict, and violence
New Auto-Interp
Negative Logits
,''
-0.77
.}
-0.72
Firstly
-0.69
\)
-0.66
|
-0.64
:
-0.64
↵
-0.64
Edit
-0.63
:)
-0.63
Firstly
-0.62
POSITIVE LOGITS
tsun
0.73
Hulu
0.67
Kardashian
0.66
humili
0.66
ueless
0.65
cannibal
0.64
hairc
0.64
endlessly
0.64
milo
0.63
lest
0.63
Activations Density 1.573%