INDEX

Explanations

gerunds and present participles

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

ingly

-0.11

INGS

-0.10

 Mund

-0.10

unted

-0.10

arm

-0.09

IZED

-0.09

Łèĥ½

-0.09

udent

-0.09

 dara

-0.09

uten

-0.09

POSITIVE LOGITS

ing

0.28

izing

0.26

ifying

0.26

uting

0.23

ening

0.23

ating

0.23

ising

0.22

ulating

0.22

uing

0.21

uating

0.21

Activations Density 0.133%