INDEX

Explanations

elements related to coding or mathematical expressions

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

 interesting

-0.07

 interess

-0.06

.Native

-0.06

 Marijuana

-0.06

rozen

-0.06

 heroin

-0.05

gebn

-0.05

 marijuana

-0.05

 mainly

-0.05

 Rencontre

-0.05

POSITIVE LOGITS

 Surge

0.12

 Simulator

0.10

 surgeon

0.09

 surgeons

0.09

 hilar

0.08

 Boss

0.08

 hilarious

0.08

 simulator

0.08

VR

0.08

 Surg

0.08

Activations Density 0.006%