INDEX

Explanations

defined, flexible, typical structure

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

 Hort

-0.09

 Burl

-0.09

Hob

-0.09

 Skinny

-0.09

 McCl

-0.08

 -*-č\n

-0.08

enes

-0.08

å¯

-0.08

unfinished

-0.08

apg

-0.08

POSITIVE LOGITS

 structure

0.59

structure

0.47

 Structure

0.46

Structure

0.41

ç»ĵæŀĦ

0.37

_structure

0.36

 ÑģÑĤÑĢÑĥÐºÑĤÑĥ

0.33

.structure

0.33

 êµ¬ì¡°

0.32

 structures

0.32

Activations Density 0.195%