INDEX
Explanations
words related to political and social issues
phrases associated with social justice issues and systemic inequalities
New Auto-Interp
Negative Logits
":"/
-0.90
owe
-0.69
uri
-0.68
iners
-0.67
IER
-0.66
imester
-0.66
obin
-0.65
PIN
-0.64
ortmund
-0.63
WARN
-0.63
POSITIVE LOGITS
etc
1.93
etc
1.72
respectively
1.03
ect
1.01
et
0.78
whatever
0.76
blah
0.74
assorted
0.73
vitamins
0.69
76561
0.69
Activations Density 0.259%