INDEX

Explanations

la followed by nouns

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

 clich

-0.11

 salopes

-0.11

 valida

-0.10

 partida

-0.10

 virus

-0.10

 declaraciÃ³n

-0.10

heimer

-0.10

 ragaz

-0.10

rop

-0.10

 talent

-0.09

POSITIVE LOGITS

 precision

0.10

 implement

0.09

alse

0.09

 redund

0.09

quelle

0.09

 whistle

0.09

 resist

0.09

 ActionController

0.09

Raz

0.08

Activations Density 0.085%