INDEX

Explanations

instances of the word "the"

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

alars

-0.08

_resolver

-0.07

lover

-0.07

à¸¢à¸¡

-0.07

æĶ¶å½ķ

-0.07

leness

-0.07

Ã¥r

-0.07

 Seas

-0.07

afari

-0.07

 Sixth

-0.06

POSITIVE LOGITS

 háºŃu

0.06

izen

0.06

 next

0.06

oret

0.06

 norm

0.06

 equivalent

0.06

iod

0.06

 pathMatch

0.05

Ä°T

0.05

Activations Density 0.006%