INDEX

Explanations

mechanical engineering and science

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

ittel

-0.09

ight

-0.09

ancellable

-0.08

estion

-0.08

idges

-0.08

CL

-0.08

 Gran

-0.08

ARSE

-0.08

 Kaynak

-0.08

-License

-0.08

POSITIVE LOGITS

anical

0.18

ancial

0.17

-elect

0.13

andise

0.12

intosh

0.12

anism

0.11

ronic

0.11

/opt

0.10

ical

0.10

Activations Density 0.025%