INDEX

Explanations

instances of surprise or unexpected events

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

.scalablytyped

-0.08

DisplayStyle

-0.07

ajs

-0.07

 thous

-0.07

ëł´

-0.07

ActivityIndicatorView

-0.07

/network

-0.07

(=)

-0.06

 Ð½ÐµÐ´ÐµÐ»Ð¸

-0.06

ÑĨÐ¸Ðº

-0.06

POSITIVE LOGITS

 surprise

0.17

 unexpected

0.17

unexpected

0.15

 Surprise

0.15

 surprises

0.15

 Unexpected

0.14

Unexpected

0.14

 unexpectedly

0.13

 surprised

0.12

 surpr

0.12

Activations Density 0.051%