INDEX

Explanations

categories and specific details

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

 Modes

-0.09

Doe

-0.09

xp

-0.08

uers

-0.08

 quint

-0.08

ite

-0.08

iler

-0.08

 evid

-0.07

ded

-0.07

 upcoming

-0.07

POSITIVE LOGITS

akest

0.09

_Lean

0.09

awy

0.08

_mE

0.08

hetics

0.08

naments

0.08

stral

0.08

 Scal

0.08

 stuff

0.08

Activations Density 0.088%