INDEX

Explanations

prepositions

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 myſelf

-0.98

 ſtate

-0.95

Попис

-0.90

Efq

-0.88

ientôt

-0.88

 whoſe

-0.87

<bos>

-0.87

ſelves

-0.87

Rüyada

-0.87

 beginnetje

-0.85

POSITIVE LOGITS

the

0.74

“

0.71

0.70

[toxicity=0]

0.63

an

0.61

 information

0.60

is

0.59

DoubleQuotes

0.58

互联网档案馆

0.58

Activations Density 3.561%