INDEX

Explanations

mentions of health and safety incidents

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

anian

-0.07

erable

-0.07

iol

-0.07

kart

-0.06

CTS

-0.06

 recipro

-0.06

ovit

-0.06

 trÃł

-0.06

.Accessible

-0.06

aktu

-0.06

POSITIVE LOGITS

 Safety

0.07

 safety

0.07

Abb

0.06

 explosion

0.06

 plant

0.06

Safety

0.06

 åĮĸ

0.06

 chemical

0.06

ACHE

0.06

lac

0.06

Activations Density 0.005%