INDEX

Explanations

references to books and their authors

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

å¸Ń

-0.07

 pieces

-0.06

naires

-0.06

ongs

-0.06

/stretch

-0.06

Ãºc

-0.06

éĽĦ

-0.05

anges

-0.05

alty

-0.05

umont

-0.05

POSITIVE LOGITS

review

0.11

-review

0.10

 review

0.10

ariant

0.08

 Review

0.08

_review

0.08

 reviewer

0.07

Review

0.07

arent

0.07

uard

0.07

Activations Density 0.020%