INDEX

Explanations

human-like states compared to ai

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

 Ð¿Ð¾Ð±Ð°

-0.10

indr

-0.09

å±Ģ

-0.09

Arb

-0.09

avery

-0.09

aram

-0.08

-Al

-0.08

omi

-0.08

ivery

-0.08

.EventHandler

-0.08

POSITIVE LOGITS

 like

0.35

 same

0.27

 zoals

0.23

 nhÆ°

0.23

åĥı

0.23

way

0.22

same

0.21

 como

0.20

 seperti

0.20

 gibi

0.19

Activations Density 0.101%