INDEX

Explanations

actions following specific qualifiers

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

quests

-0.10

¶Į

-0.10

.FindGameObjectWithTag

-0.09

egra

-0.09

 Herrera

-0.08

ÐºÐ¾Ð´

-0.08

 DISPATCH

-0.08

 strand

-0.08

azon

-0.08

POSITIVE LOGITS

 vote

0.14

 request

0.12

 query

0.12

 review

0.12

 attack

0.12

 appeal

0.11

 report

0.11

vote

0.10

 claim

0.10

cry

0.10

Activations Density 0.170%