INDEX

Explanations

fine, thin, gray, blurred state

New Auto-Interp

Top Features by Cosine Similarity

Configuration

Prompts (Dashboard)

10,000 prompts, 128 tokens each

Dataset (Dashboard)

lmsys/lmsys-chat-1m

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cola

-0.09

 mildly

-0.09

viron

-0.09

 rainbow

-0.09

_DT

-0.09

wner

-0.08

 typically

-0.08

ÏĢÎ¹Ïĥ

-0.08

 colder

-0.08

poc

-0.08

POSITIVE LOGITS

 thin

0.33

 fine

0.33

 gray

0.32

 grey

0.29

 Thin

0.28

 Fine

0.28

fine

0.26

 blurred

0.26

 Gray

0.26

 blur

0.24

Activations Density 0.183%