INDEX

Explanations

concepts related to respect and equality in human 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

ofire

-0.08

erra

-0.06

teÅŁ

-0.06

cname

-0.06

IQUE

-0.06

ãĥ³ãĥĩ

-0.06

ORE

-0.06

Assertions

-0.06

MethodInfo

-0.06

ublish

-0.06

POSITIVE LOGITS

 treatment

0.49

 Treatment

0.43

 treat

0.40

 treating

0.39

 treated

0.39

 treatments

0.38

Treatment

0.36

 Treat

0.36

 treats

0.34

-treated

0.33

Activations Density 0.203%