INDEX

Explanations

types of things

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

URN

-0.10

 Strings

-0.10

orgen

-0.10

strings

-0.09

UPC

-0.09

tep

-0.08

 Ð¾Ñĩ

-0.08

ocities

-0.08

_traits

-0.08

POSITIVE LOGITS

 types

0.23

 kinds

0.19

 type

0.18

ç±»åŀĭ

0.15

 concepts

0.15

 operations

0.15

 techniques

0.14

types

0.14

 sorts

0.14

 structures

0.13

Activations Density 0.219%