INDEX

Explanations

Survivor show title

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

 movie

-0.14

 filme

-0.12

 movies

-0.12

 pelÃŃcula

-0.12

movie

-0.12

éĽ»å½±

-0.11

 film

-0.11

 Movie

-0.11

æĺłçĶ»

-0.11

 films

-0.10

POSITIVE LOGITS

 season

0.25

 Season

0.23

 seasons

0.21

Season

0.20

 creator

0.20

 ìĭľì¦Į

0.19

 series

0.18

 show

0.17

-season

0.17

 Seasons

0.17

Activations Density 0.080%