INDEX

Explanations

references to cultural expressions and practices

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

ccione

-0.07

Ø°ÙĬ

-0.07

 Laud

-0.07

kf

-0.07

 Hate

-0.07

ocre

-0.06

roj

-0.06

 Scient

-0.06

educ

-0.06

RefCount

-0.06

POSITIVE LOGITS

 anthropology

0.09

anth

0.07

 anthrop

0.07

 field

0.07

Ì£

0.07

 village

0.07

 villagers

0.07

kin

0.07

 Classic

0.06

field

0.06

Activations Density 0.064%