INDEX

Explanations

language related to safety regulations and monitoring systems

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

Ð»Ð°Ð´Ð¸

-0.06

 inversion

-0.06

thon

-0.06

 procession

-0.06

onn

-0.06

deg

-0.05

 rings

-0.05

ervoir

-0.05

inem

-0.05

POSITIVE LOGITS

 fire

0.11

 Fire

0.10

Fire

0.10

.Fire

0.09

_fire

0.09

 FIRE

0.09

/fire

0.08

-fire

0.08

çģ«

0.08

fire

0.07

Activations Density 0.003%