INDEX

Explanations

current changes and contexts

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

_blocking

-0.09

oq

-0.09

-old

-0.09

ities

-0.08

 Laden

-0.08

quals

-0.08

 stap

-0.08

ologies

-0.08

 alot

-0.08

 barber

-0.08

POSITIVE LOGITS

 current

0.15

ext

0.11

how

0.10

 changes

0.10

 recent

0.10

 broader

0.10

 shifts

0.10

 ongoing

0.10

 existing

0.10

\tcurrent

0.09

Activations Density 0.147%