INDEX

Explanations

Indexes images and labels

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

 informiert

0.39

 disappointing

0.39

anska

0.39

 Simone

0.39

ۚ

0.39

벙

0.38

žem

0.38

 behaved

0.37

 Minds

0.37

 revived

0.37

POSITIVE LOGITS

 Хоккей

0.49

Energy

0.46

```

0.46

 название

0.45

Buffer

0.45

Charge

0.45

 étale

0.45

 tweak

0.45

く

0.45

ერ

0.44

Activations Density 0.003%