INDEX

Explanations

references to historical places or architecture

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

aphael

-0.09

izzer

-0.08

estar

-0.07

icode

-0.07

dete

-0.07

 merak

-0.07

SCP

-0.07

kate

-0.07

ipes

-0.07

YE

-0.07

POSITIVE LOGITS

 Clair

0.09

 Benedict

0.08

 Font

0.08

 foundation

0.08

 reform

0.08

 Chart

0.08

ben

0.07

 Eins

0.07

Cl

0.07

 regular

0.07

Activations Density 0.007%