INDEX

Explanations

the word "high"

high

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

 high

-2.48

high

-2.23

High

-1.91

 High

-1.81

 HIGH

-1.57

HIGH

-1.50

高

-1.42

 alta

-1.30

的高

-1.29

 hohe

-1.27

POSITIVE LOGITS

出版年

0.87

+#+#

0.80

providedIn

0.74

interopRequire

0.67

Pratique

0.66

AndEndTag

0.65

RenderAtEndOf

0.63

ometrica

0.60

 OFDb

0.59

tahui

0.59

Activations Density 0.384%