INDEX

Explanations

terms indicating insignificance or triviality

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

solete

-0.08

atica

-0.07

 maybe

-0.07

tober

-0.07

smith

-0.07

printStats

-0.06

hora

-0.06

scr

-0.06

hots

-0.06

stairs

-0.06

POSITIVE LOGITS

à¹Ĩ

0.09

mente

0.08

 dint

0.08

Ã¡no

0.07

chants

0.07

est

0.07

.Mouse

0.07

ĶåĽŀ

0.07

tons

0.07

ocab

0.07

Activations Density 0.004%