INDEX
Explanations
words related to the material "steel."
occurrences of the word "steel."
New Auto-Interp
Negative Logits
Kard
-0.83
erenn
-0.70
[|
-0.70
itia
-0.69
olulu
-0.68
Garr
-0.67
romeda
-0.67
NCT
-0.65
HIP
-0.64
DOE
-0.64
POSITIVE LOGITS
wool
1.10
works
1.02
Series
1.00
workers
0.95
worker
0.93
fish
0.93
oxide
0.91
anguage
0.89
beams
0.88
Steel
0.85
Activations Density 0.008%