INDEX

Explanations

concepts related to uncertainty and decision-making

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

keit

-0.06

ruh

-0.06

WithPath

-0.06

vals

-0.06

ÏĦÎ¿ÏħÏĤ

-0.06

 woes

-0.06

çĹ

-0.06

ara

-0.06

ÐĵÐŀ

-0.05

POSITIVE LOGITS

 unknown

0.16

 Unknown

0.14

 unpredictable

0.14

unknown

0.14

 uncertain

0.13

 UNKNOWN

0.13

Unknown

0.12

_unknown

0.12

 uncertainty

0.12

Unc

0.12

Activations Density 0.048%