INDEX

Explanations

leave it behind

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

-0.09

reuse

-0.09

.foundation

-0.09

 Nile

-0.09

rv

-0.09

indle

-0.09

itore

-0.09

arness

-0.08

ascript

-0.08

POSITIVE LOGITS

 behind

0.22

CriticalSection

0.17

 Behind

0.16

Behind

0.14

 alone

0.14

 khá»ıi

0.13

beh

0.13

 town

0.13

 room

0.13

-alone

0.12

Activations Density 0.020%