INDEX
Explanations
terms related to various forms of oppression and injustice
New Auto-Interp
Negative Logits
تÙĪÙĨ
-0.16
opposition
-0.16
olina
-0.15
ldr
-0.15
Animations
-0.14
opposite
-0.14
Opposition
-0.14
$MESS
-0.14
ually
-0.14
agr
-0.14
POSITIVE LOGITS
zech
0.15
incident
0.14
447
0.14
incidental
0.14
WB
0.14
don
0.14
incident
0.14
ÂŃs
0.13
aug
0.13
UGIN
0.13
Activations Density 0.014%