INDEX

Explanations

improving something

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 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

 &___

-0.68

Rüyada

-0.65

 doInBackground

-0.60

UniformLocation

-0.60

RetentionPolicy

-0.60

ismet

-0.59

URLException

-0.58

 AppDelegate

-0.57

ValueStyle

-0.57

 culturelles

-0.55

POSITIVE LOGITS

 access

0.52

 household

0.52

liv

0.50

<bos>

0.50

 maíz

0.50

 food

0.50

\"");

0.50

!';

0.49

 Horn

0.46

 Más

0.46

Activations Density 0.003%