INDEX

Explanations

example of a simple

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

 examples

-0.11

_RM

-0.09

 Kend

-0.09

 Examples

-0.09

Examples

-0.08

ajo

-0.08

examples

-0.08

Pon

-0.08

odd

-0.08

 tieten

-0.08

POSITIVE LOGITS

 simple

0.28

ç®Ģåįķ

0.22

 basic

0.21

simple

0.19

 typical

0.17

åŁºæľ¬

0.17

basic

0.16

 Ð¿ÑĢÐ¾ÑģÑĤ

0.16

ç°¡

0.15

 simples

0.15

Activations Density 0.134%