INDEX

Explanations

modals indicating outcomes

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

zed

-0.09

stakes

-0.09

achi

-0.09

plex

-0.09

 creep

-0.09

 Crowley

-0.09

 plunge

-0.09

OPS

-0.09

-0.08

/UIKit

-0.08

POSITIVE LOGITS

 driving

0.19

 drive

0.18

åĪº

0.16

 drives

0.16

 prop

0.15

sp

0.15

 fuel

0.14

 drove

0.14

 translated

0.13

drive

0.13

Activations Density 0.062%