INDEX

Explanations

comparative phrases emphasizing quantities or qualities

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Much

-0.10

much

-0.10

 much

-0.10

 certain

-0.10

 MUCH

-0.09

Much

-0.09

 Certain

-0.08

éĨĴ

-0.07

erman

-0.07

 Ø¨Ø³

-0.07

POSITIVE LOGITS

 like

0.08

 about

0.08

eso

0.06

 Like

0.06

etin

0.06

 contr

0.06

 Illegal

0.06

untime

0.06

bl

0.06

eti

0.06

Activations Density 0.021%