INDEX

Explanations

b followed by numbers

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

duk

-0.10

 McKin

-0.08

.DependencyInjection

-0.08

à¹Īà¸ĩà¸Ĥ

-0.08

hcp

-0.08

 Pike

-0.08

/Core

-0.08

-generic

-0.08

idor

-0.08

.LayoutStyle

-0.08

POSITIVE LOGITS

Looper

0.10

azzi

0.10

*pow

0.10

 forth

0.09

 Martian

0.09

Ã¶l

0.09

ressing

0.08

iena

0.08

.Ptr

0.08

 Merrill

0.08

Activations Density 0.033%