INDEX

Explanations

references to gendered terms and familial relationships

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

à¤¾à¤¹à¤ķ

-0.07

LAT

-0.06

awe

-0.06

çĭ¼

-0.06

[of

-0.06

itary

-0.06

itura

-0.06

à¤¾à¤¹

-0.06

hd

-0.06

atre

-0.06

POSITIVE LOGITS

 Dead

0.10

 dead

0.09

Dead

0.08

.dead

0.08

dead

0.08

(dead

0.07

 DEAD

0.07

andra

0.07

 walking

0.06

_dead

0.06

Activations Density 0.006%