INDEX

Explanations

lived in/by/with

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

itten

-0.09

amedi

-0.09

 unmanned

-0.09

Chu

-0.09

anks

-0.09

amble

-0.09

.IsNullOr

-0.08

levant

-0.08

 alive

-0.08

halb

-0.08

POSITIVE LOGITS

stone

0.14

ston

0.13

ëŁ¬ë¦¬

0.12

/work

0.12

alone

0.11

-action

0.11

-stream

0.11

 thá»į

0.10

 alone

0.10

 paycheck

0.10

Activations Density 0.033%