INDEX

Explanations

Royal and associated terms

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

edList

-0.10

sk

-0.10

agram

-0.09

ories

-0.09

ese

-0.08

lamp

-0.08

sert

-0.08

arel

-0.08

aise

-0.08

Jvm

-0.08

POSITIVE LOGITS

TY

0.16

 flush

0.15

 Flush

0.14

alty

0.13

ston

0.13

ist

0.13

autÃ©

0.12

 jelly

0.11

_FLUSH

0.11

flush

0.11

Activations Density 0.028%