INDEX

Explanations

authors' names and related works

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

inist

0.50

0.49

wood

0.48

 וה

0.48

ikk

0.47

smouth

0.47

erman

0.47

and

0.46

<0xE8>

0.45

 $^{\

0.45

POSITIVE LOGITS

 lucrative

0.56

 elongated

0.56

 다양한

0.51

 diligent

0.51

 patip

0.51

 flimsy

0.50

 passaggio

0.49

 flawless

0.48

memset

0.48

 beings

0.48

Activations Density 0.025%