INDEX

Explanations

When

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ellen

0.79

 horribly

0.78

😡

0.74

꼭

0.70

carp

0.69

 monstru

0.69

 fenomeno

0.69

 isten

0.68

 terrible

0.68

🤦

0.68

POSITIVE LOGITS

 uncertainty

3.33

 uncertainties

3.08

 doubt

3.02

 Uncertainty

2.99

 doubts

2.88

uncertain

2.87

 uncertain

2.70

 Uncertain

2.66

 incertid

2.56

doubt

2.43

Activations Density 0.196%