INDEX

Explanations

Nonsense

words suggesting conflict or harm and formal documents

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

Negative Logits

васто

-0.52

 smart

-0.50

//

-0.50

sli

-0.47

#!

-0.46

 just

-0.44

ardi

-0.44

 OFDb

-0.44

 mere

-0.42

 letters

-0.41

POSITIVE LOGITS

 kasarigan

0.81

 насељу

0.68

WriteAttribute

0.68

prepareStatement

0.67

antaranya

0.64

nodoc

0.64

󠁿

0.64

 télécharge

0.62

AccessorTable

0.62

исленность

0.61

Activations Density 6.337%