INDEX

Explanations

Sont considÃ©rÃ©es couvrant

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

 Bever

-0.10

Fur

-0.09

å

-0.09

ANDLE

-0.09

 enorm

-0.09

hir

-0.09

ousse

-0.09

-0.08

/media

-0.08

 malign

-0.08

POSITIVE LOGITS

 mention

0.12

 Mention

0.12

 mentions

0.11

 primo

0.10

 convention

0.10

ÑİÑĢ

0.10

-âĢĲ

0.10

JOR

0.10

 Modal

0.10

axe

0.10

Activations Density 0.096%