INDEX
Explanations
information related to political and social issues
references to social issues and movements
New Auto-Interp
Negative Logits
estones
-0.55
oulos
-0.55
OIL
-0.52
xtap
-0.52
-0.51
UGC
-0.50
estone
-0.50
isu
-0.50
âĨij
-0.49
ROR
-0.49
POSITIVE LOGITS
..."
1.23
â̦"
1.15
fuckin
1.03
â̦"
1.01
â̦."
0.94
..."
0.94
fucking
0.93
"?
0.92
goddamn
0.91
gonna
0.89
Activations Density 1.427%