INDEX

Explanations

mix of different

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

 identical

-0.11

 respective

-0.09

atu

-0.09

irit

-0.09

undef

-0.09

icter

-0.09

loh

-0.08

adera

-0.08

 sophistic

-0.08

 bestimm

-0.08

POSITIVE LOGITS

 different

0.20

 types

0.20

mix

0.16

 TYPES

0.15

 variety

0.15

 diferentes

0.15

different

0.15

ä¸įåĲĮ

0.15

Different

0.14

 Different

0.14

Activations Density 0.060%