INDEX

Explanations

known for his novels

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

nut

-0.10

 cartoon

-0.10

 Poetry

-0.09

æī¶

-0.09

ooke

-0.09

 Cartoon

-0.09

 slack

-0.09

Pam

-0.09

 Final

-0.09

 cartoons

-0.08

POSITIVE LOGITS

 realistic

0.17

 novel

0.16

 novels

0.15

 realism

0.15

nov

0.12

ãĥªãĤ¢

0.11

 roman

0.11

 Novel

0.10

 Sinclair

0.10

 sentimental

0.10

Activations Density 0.058%