INDEX

Explanations

You're not helping

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

eyse

-0.10

datatable

-0.09

 bust

-0.09

swick

-0.09

 Guests

-0.09

isle

-0.09

 ï½¤

-0.09

 bump

-0.09

POR

-0.08

.scalablytyped

-0.08

POSITIVE LOGITS

 vict

0.17

 victory

0.15

 victorious

0.13

 Victory

0.13

ä¿

0.13

 boot

0.12

 kicks

0.12

 stood

0.12

 kicking

0.12

Vict

0.12

Activations Density 0.037%