INDEX

Explanations

possessive adjectives and pronouns related to individuals

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

owo

-0.09

eld

-0.08

ugs

-0.07

hai

-0.07

olves

-0.07

 thiÃªn

-0.07

aidu

-0.06

 teÅŁkil

-0.06

uzey

-0.06

ovo

-0.06

POSITIVE LOGITS

in

0.07

 case

0.06

 absence

0.06

amet

0.06

cleanup

0.06

ÙĪØªÛĮ

0.06

ammer

0.06

agr

0.06

 spare

0.06

Activations Density 0.017%