INDEX
Explanations
phrases describing exceptional mental and physical abilities associated with gender
New Auto-Interp
Negative Logits
'options
-0.17
irit
-0.16
arma
-0.15
ugin
-0.15
kp
-0.15
ropa
-0.15
δά
-0.15
Obst
-0.14
Empresa
-0.14
æµľ
-0.14
POSITIVE LOGITS
intelligence
0.17
wiring
0.17
trait
0.16
ability
0.15
Intelligence
0.15
IQ
0.15
flick
0.14
bypass
0.14
IQ
0.14
004
0.14
Activations Density 0.072%