INDEX
Explanations
exclamations of surprise or relief
New Auto-Interp
Negative Logits
Deleg
0.40
выде
0.39
Yep
0.38
Delegation
0.38
Placeholder
0.37
ziemlich
0.36
रेट
0.36
Tough
0.36
Proof
0.35
😎
0.35
POSITIVE LOGITS
heavens
1.50
goodness
1.41
heaven
1.34
gods
1.28
god
1.23
God
1.20
God
1.19
Heaven
1.14
Heaven
1.13
Gods
1.12
Activations Density 0.024%