INDEX

Explanations

unique properties and

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

oba

-0.12

ary

-0.11

uba

-0.10

tr

-0.09

ishi

-0.09

naires

-0.09

resi

-0.09

trer

-0.09

 warped

-0.09

 Hakk

-0.08

POSITIVE LOGITS

(properties

0.13

 properties

0.11

/functions

0.10

eties

0.10

(Properties

0.10

ÙħØ¯

0.09

ouns

0.09

(Property

0.09

-properties

0.09

íĸ¥

0.09

Activations Density 0.021%