INDEX

Explanations

phrases expressing uncertainty or lack of knowledge

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

uta

-0.07

utz

-0.07

-anchor

-0.07

atta

-0.06

dig

-0.06

Otherwise

-0.06

deme

-0.06

Cheers

-0.06

 otherwise

-0.06

elib

-0.06

POSITIVE LOGITS

 answer

0.10

.answer

0.10

answer

0.10

 answered

0.10

 Answer

0.09

åĽŀçŃĶ

0.09

answered

0.09

 answering

0.08

(answer

0.08

Answer

0.07

Activations Density 0.023%