INDEX

Explanations

in addition or in 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

 anticipation

-0.11

 tandem

-0.10

 Farr

-0.08

errupted

-0.08

á»©

-0.08

 institution

-0.08

deÅŁ

-0.08

 æĸ¼

-0.08

 connexion

-0.08

iet

-0.08

POSITIVE LOGITS

 addition

0.23

 terms

0.22

 Addition

0.15

 recent

0.14

terms

0.13

 additions

0.13

 TERMS

0.12

add

0.12

 Terms

0.12

 line

0.12

Activations Density 0.008%