INDEX
Explanations
terms and phrases related to civil rights and discrimination issues
New Auto-Interp
Negative Logits
dip
-0.15
Dip
-0.15
iasi
-0.14
ipp
-0.14
aus
-0.14
api
-0.14
aktu
-0.14
nic
-0.14
rone
-0.14
API
-0.14
POSITIVE LOGITS
sworth
0.16
alta
0.16
Intelligence
0.15
ź
0.14
avage
0.14
ï¸
0.14
.Metadata
0.14
****************************************************************************
0.14
ometr
0.14
bul
0.13
Activations Density 0.003%