INDEX
Explanations
concepts related to equality and equal treatment in various contexts, especially concerning gender and social relationships
New Auto-Interp
Negative Logits
дово
-0.51
DebuggerNonUser
-0.49
مشين
-0.48
背
-0.47
yng
-0.46
bitos
-0.46
Rapid
-0.46
elt
-0.45
riko
-0.44
ಂದ
-0.44
POSITIVE LOGITS
equal
2.41
equal
2.07
Equal
2.02
EQUAL
1.94
Equal
1.86
equality
1.80
equals
1.71
égal
1.69
equally
1.67
igual
1.55
Activations Density 0.474%