INDEX

Explanations

phrases that assess or describe quality and value in a context

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

usz

-0.06

 Pearce

-0.06

Entities

-0.06

misc

-0.06

fo

-0.06

ws

-0.05

Ð°Ð½Ð¾Ð²

-0.05

à¸ļà¸¥

-0.05

Ease

-0.05

ws

-0.05

POSITIVE LOGITS

way

0.10

 ways

0.08

 GOOD

0.08

-way

0.07

 good

0.07

Way

0.07

WAY

0.07

way

0.07

 kind

0.07

wdx

0.07

Activations Density 0.012%