INDEX
Explanations
instances of the word "proposition."
New Auto-Interp
Negative Logits
hindurch
-0.49
s
-0.46
Semoga
-0.43
Wah
-0.42
nôtre
-0.42
Hanya
-0.42
дравству
-0.42
suivez
-0.41
Noruega
-0.41
BorderSide
-0.41
POSITIVE LOGITS
proposition
2.27
Proposition
1.96
proposition
1.92
Proposition
1.84
propositions
1.84
PROPOS
0.94
Prop
0.90
prop
0.89
propos
0.87
proposal
0.82
Activations Density 0.016%