INDEX

Explanations

include some list items

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

 peel

0.42

 disrespectful

0.38

sstream

0.37

icias

0.37

 części

0.37

ției

0.36

tmpobj

0.36

 wired

0.36

jit

0.36

,-\

0.36

POSITIVE LOGITS

 Kawasaki

0.44

 Know

0.44

 Visualization

0.43

 Sweet

0.41

 Beautiful

0.41

 Still

0.41

 Innovation

0.41

('

0.40

 („

0.39

『

0.38

Activations Density 0.000%