INDEX
Explanations
words related to a specific code name
mentions of "cod."
New Auto-Interp
Negative Logits
enger
-0.74
ason
-0.70
Rush
-0.69
Loans
-0.68
Stadium
-0.68
Ride
-0.67
Pu
-0.66
Shoes
-0.66
Pa
-0.65
ieu
-0.64
POSITIVE LOGITS
cod
4.21
Cod
2.42
Cod
2.35
cod
2.16
Codex
1.36
coding
1.10
Codec
1.03
code
1.00
coded
0.97
declass
0.97
Activations Density 0.012%