INDEX

Explanations

mentions of individuals and their associated works or contributions

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Darling

-0.07

ioc

-0.06

 fabulous

-0.06

-wsj

-0.06

istes

-0.06

§è¡Į

-0.05

ecn

-0.05

 television

-0.05

Experts

-0.05

 delightful

-0.05

POSITIVE LOGITS

 fuck

0.12

 shit

0.12

 fucked

0.12

 fucking

0.12

 mates

0.12

fuck

0.11

 mate

0.11

 fucks

0.11

 Fuck

0.11

Fuck

0.10

Activations Density 0.023%