INDEX

Explanations

admin /add /post

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

 Coun

-0.10

Hir

-0.10

 Guest

-0.09

elm

-0.09

ande

-0.09

iture

-0.09

 Alman

-0.09

ERSHEY

-0.09

Wer

-0.09

emic

-0.08

POSITIVE LOGITS

.ModelAdmin

0.21

 admin

0.19

admin

0.18

(admin

0.16

 administration

0.16

 Admin

0.14

.admin

0.13

@admin

0.13

Admin

0.12

 Administration

0.12

Activations Density 0.008%