INDEX

Explanations

words that describe something being of high or low quality

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

time

-0.63

 Dase

-0.62

UrlResolution

-0.62

rungsseite

-0.60

Hef

-0.60

<em>

-0.58

 tain

-0.58

λαν

-0.58

<i>

-0.57

 Alli

-0.57

POSITIVE LOGITS

 Inferior

1.22

帖最后由

1.16

 Superior

1.15

 SUPERIOR

1.15

Superior

1.14

superior

1.14

inferior

1.10

 inferior

0.99

 supérieure

0.97

 supérieur

0.97

Activations Density 0.007%