INDEX

Explanations

phrases indicating desire or intent

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

alem

-0.07

/kernel

-0.07

erk

-0.07

à¸±à¸ķà¸Ļ

-0.07

zk

-0.07

vla

-0.07

ÏĨÎ¿

-0.07

 Susp

-0.06

 inse

-0.06

à¸·à¹ī

-0.06

POSITIVE LOGITS

Ð¾ÑģÑĮ

0.07

ieder

0.07

lix

0.06

cloak

0.06

Setter

0.06

Builders

0.06

ondo

0.06

 hearing

0.06

DSL

0.06

Activations Density 0.019%