INDEX

Explanations

words related to attempts or efforts to achieve something

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

smith

-0.08

mond

-0.07

heit

-0.07

-ÑĤÐ¾

-0.07

TimeInterval

-0.07

ÑĩÐ°ÑĤ

-0.07

strap

-0.07

ialized

-0.07

 Affero

-0.07

ulings

-0.07

POSITIVE LOGITS

to

0.09

ively

0.08

entially

0.07

ive

0.07

aly

0.07

inger

0.07

 feats

0.06

INGER

0.06

 feat

0.06

Activations Density 0.011%