INDEX

Explanations

past tense verbs and prepositions

numerical terms and quantitative expressions

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

has

-0.59

 since

-0.58

 have

-0.55

 been

-0.54

since

-0.50

 Since

-0.49

Since

-0.48

has

-0.47

wijl

-0.45

had

-0.45

POSITIVE LOGITS

 propOrder

0.79

Efq

0.75

 Мексичка

0.71

 dozens

0.69

 hundreds

0.67

تقاوى

0.66

Thousands

0.66

 rhestr

0.66

jacency

0.65

OGND

0.65

Activations Density 7.132%