INDEX

Explanations

multilingual affirmations

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

uld

-0.09

deg

-0.09

 Sans

-0.09

iar

-0.09

 Ð´ÑĥÐ¼Ð°

-0.08

ä¼¼

-0.08

''''

-0.08

 Sergio

-0.08

.firstChild

-0.08

Lib

-0.08

POSITIVE LOGITS

 pleasure

0.13

å½ĵçĦ¶

0.13

 absolutely

0.12

 sure

0.12

 Sure

0.12

sure

0.12

Sure

0.11

fine

0.11

åı¯ä»¥

0.11

Jaw

0.10

Activations Density 0.188%