INDEX

Explanations

concepts of morality and the consequences of actions

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Embeds

IFrame

Link

Negative Logits

 Maher

-0.07

ette

-0.06

.navigationItem

-0.06

 basics

-0.06

cola

-0.06

Monkey

-0.05

MPG

-0.05

vo

-0.05

HideInInspector

-0.05

ãĥ«ãĥĪ

-0.05

POSITIVE LOGITS

 instead

0.22

instead

0.20

Instead

0.18

 Instead

0.17

 Ð²Ð¼ÐµÑģÑĤ

0.17

ãģ§ãģ¯ãģªãģı

0.10

 inve

0.10

 statt

0.10

 rather

0.09

 naopak

0.09

Activations Density 0.068%

No Known Activations