INDEX

Explanations

instagram posts and accounts

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

 Tweets

-0.16

 tweeting

-0.14

 tweet

-0.14

 tweeted

-0.14

 tweets

-0.13

 Tweet

-0.13

Tweet

-0.12

 twitter

-0.10

ysi

-0.10

tweets

-0.09

POSITIVE LOGITS

IG

0.27

IG

0.21

 Inst

0.20

.instagram

0.20

 Instagram

0.18

 Stories

0.18

Inst

0.17

ig

0.16

Instagram

0.16

.Inst

0.15

Activations Density 0.068%