INDEX
Explanations
references to steel or related terms in various contexts
New Auto-Interp
Negative Logits
es
-0.19
etic
-0.16
asu
-0.16
eldon
-0.15
elli
-0.15
ï
-0.15
elenium
-0.15
eks
-0.14
enza
-0.14
ãĥ³ãĥĩ
-0.14
POSITIVE LOGITS
workers
0.25
making
0.21
worker
0.21
works
0.20
wool
0.19
licity
0.18
رد
0.18
çIJ´
0.17
stown
0.17
makers
0.16
Activations Density 0.008%