INDEX
Explanations
themes related to educational and social inequities
New Auto-Interp
Negative Logits
pawn
-0.07
eya
-0.06
oga
-0.06
errated
-0.06
à¹īà¸Ńม
-0.06
essel
-0.06
idar
-0.06
vil
-0.06
ulk
-0.06
plen
-0.06
POSITIVE LOGITS
gap
0.08
Gap
0.07
between
0.07
stubborn
0.07
gap
0.07
difference
0.07
Magn
0.07
between
0.07
persist
0.06
Gap
0.06
Activations Density 0.010%