INDEX

Explanations

user prompts in various languages

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

¶Į

-0.16

Msp

-0.13

EMPLARY

-0.10

«ng

-0.10

PFN

-0.09

įng

-0.09

³ç´°

-0.09

<|begin_of_text|>

-0.09

 CAUSED

-0.09

-------------</

-0.09

POSITIVE LOGITS

apan

0.10

/c

0.10

ãģħ

0.09

 perc

0.09

 Hedge

0.09

Gow

0.08

 Chand

0.08

Gra

0.08

Activations Density 0.005%