INDEX
Explanations
references to various industries
New Auto-Interp
Negative Logits
.infinity
-0.17
svens
-0.15
arat
-0.15
mont
-0.14
filmer
-0.14
deniz
-0.14
urer
-0.14
DS
-0.14
bum
-0.14
onda
-0.13
POSITIVE LOGITS
alis
0.16
arga
0.15
_exports
0.15
dge
0.14
į°
0.14
890
0.14
insic
0.14
важ
0.13
ories
0.13
slt
0.13
Activations Density 0.011%