INDEX

Explanations

phrases that indicate causation or underlying reasons

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

Äįer

-0.07

/ion

-0.07

æ³£

-0.07

eced

-0.07

uro

-0.06

Ð»ÐµÐ¼

-0.06

ÑĢÐ¾ÑģÑĤ

-0.06

idal

-0.06

sin

-0.06

ion

-0.06

POSITIVE LOGITS

illard

0.07

æĸ¼

0.06

avs

0.06

akis

0.06

 lack

0.06

 CHARSET

0.06

ogui

0.06

neath

0.06

Coder

0.06

Rated

0.06

Activations Density 0.014%