INDEX
Explanations
mentions of discrimination in various contexts, particularly related to civil rights and social issues
New Auto-Interp
Negative Logits
lify
-0.17
okud
-0.16
massaggi
-0.16
onia
-0.14
xOffset
-0.14
Burr
-0.14
.wr
-0.14
AAA
-0.14
ιν
-0.14
.ActionBar
-0.14
POSITIVE LOGITS
-ng
0.16
oftware
0.15
ophobic
0.15
.scalablytyped
0.15
ackson
0.14
showers
0.14
ately
0.14
ãĥ³ãĤ°ãĥ«
0.14
isor
0.14
lich
0.13
Activations Density 0.007%