INDEX

Explanations

string formatting operations `.format` `encode` `split`

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

::.

-0.11

avan

-0.09

alt

-0.09

unm

-0.09

alt

-0.09

 Bruno

-0.08

 Ming

-0.08

{'

-0.08

(trim

-0.08

 Alleg

-0.08

POSITIVE LOGITS

format

0.23

.format

0.23

 format

0.20

-format

0.16

\tformat

0.15

Format

0.14

 formats

0.14

 Format

0.13

æł¼å¼ı

0.13

 formato

0.13

Activations Density 0.019%