INDEX

Explanations

multiple occurrences

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

zeit

-0.10

uria

-0.10

 Kings

-0.09

azo

-0.09

uin

-0.09

 Hend

-0.09

_initializer

-0.09

xis

-0.09

ified

-0.09

STALL

-0.09

POSITIVE LOGITS

çĽ®ãģ®

0.13

 times

0.12

cales

0.12

(times

0.11

 veces

0.11

ë¡Ģ

0.10

 divorced

0.10

over

0.10

-over

0.10

ÑĢÐ°ÑĤÐ½Ð¾

0.10

Activations Density 0.053%