INDEX
Explanations
references to military and defense-related topics
New Auto-Interp
Negative Logits
><?
-0.15
agement
-0.15
pta
-0.14
kola
-0.14
TYPO
-0.14
ез
-0.14
dej
-0.14
梨
-0.14
PCA
-0.14
zug
-0.14
POSITIVE LOGITS
research
0.26
Research
0.23
research
0.23
çłĶç©¶
0.21
Research
0.20
technological
0.20
researching
0.19
researchers
0.19
technical
0.18
testing
0.18
Activations Density 0.379%