INDEX

Explanations

That's a really interesting

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

 нередко

0.46

 tacit

0.44

 fortiter

0.44

၌

0.43

 شوند

0.42

竅

0.41

 mutate

0.41

ńskich

0.41

何を

0.41

wherein

0.41

POSITIVE LOGITS

 Really

0.87

 Overall

0.78

 Honestly

0.75

 really

0.71

Really

0.70

真的是

0.64

 Definitely

0.64

Honestly

0.63

Overall

0.62

 honestly

0.59

Activations Density 0.000%