INDEX
Explanations
references to nickel and its compounds or derivatives
New Auto-Interp
Negative Logits
igm
-0.16
tain
-0.16
Pierce
-0.15
ils
-0.15
iaux
-0.15
ansa
-0.15
esy
-0.15
er
-0.15
es
-0.14
oj
-0.14
POSITIVE LOGITS
ode
0.25
nick
0.19
olson
0.19
odem
0.17
olas
0.16
Nickel
0.16
mith
0.16
hill
0.15
elsen
0.15
bread
0.15
Activations Density 0.006%