INDEX

Explanations

articles preceding nouns indicating significant concepts or categories

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

ies

-0.07

 subsequ

-0.07

 ones

-0.07

iez

-0.07

idor

-0.07

ãĤĪãģĨãģ«

-0.07

ÑĨÑĥ

-0.06

eses

-0.06

jes

-0.06

nowledge

-0.06

POSITIVE LOGITS

coli

0.07

ëį°

0.07

acent

0.07

/tiny

0.07

 Thing

0.07

antity

0.07

ITY

0.06

Ð»Ð¸Ð¼

0.06

Ł

0.06

orex

0.06

Activations Density 0.012%