INDEX

Explanations

logic

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

vement

-0.94

vances

-0.62

ed

-0.62

apimachinery

-0.61

vance

-0.59

gonic

-0.58

يكب

-0.58

енча

-0.58

ically

-0.57

vements

-0.57

POSITIVE LOGITS

RenderAtEndOf

0.75

WebElementEntity

0.55

+#+#

0.53

 thermique

0.52

EndProject

0.50

 externi

0.49

ohner

0.48

#__

0.48

[]:

0.47

帖最后由

0.46

Activations Density 0.045%