INDEX

Explanations

particular, crucial, inaugural

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

Til

-0.09

 alias

-0.09

-native

-0.09

Traits

-0.09

audi

-0.09

apos

-0.09

 proper

-0.08

amin

-0.08

çľŁæŃ£

-0.08

 Ø¨ÛĮØ´ØªØ±ÛĮ

-0.08

POSITIVE LOGITS

-ci

0.15

 particular

0.12

-l

0.11

 Hlav

0.11

elden

0.10

tte

0.09

 inaugural

0.09

 PARTICULAR

0.09

Ø¹Ø§

0.09

 crucial

0.09

Activations Density 0.111%