INDEX

Explanations

references to legal proceedings and accountability related to accidents

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

å½±

-0.06

idel

-0.06

 Holt

-0.06

uchs

-0.06

 Vogue

-0.06

Jed

-0.06

filtro

-0.06

alg

-0.06

iti

-0.06

 Sorting

-0.06

POSITIVE LOGITS

 Safety

0.11

 safety

0.11

Safety

0.10

 unsafe

0.10

 accident

0.10

afety

0.10

 Accident

0.09

 Unsafe

0.08

 accidents

0.08

 crash

0.08

Activations Density 0.008%