INDEX

Explanations

references to individual physical or biological attributes and systems

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

anje

-0.07

æ¬

-0.07

ÙĦÙģØ©

-0.07

HORT

-0.07

 CONSEQUENTIAL

-0.07

eniz

-0.07

urette

-0.07

OKEN

-0.06

itchens

-0.06

riet

-0.06

POSITIVE LOGITS

 body

0.33

 bodies

0.29

body

0.28

-body

0.27

 Body

0.25

bod

0.25

 BODY

0.24

Body

0.24

 Bodies

0.23

_body

0.23

Activations Density 0.035%