INDEX

Explanations

proper nouns, especially brand and publication names

seemingly random text fragments

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

 inš

-0.51

witz

-0.51

 kyllä

-0.50

tagext

-0.49

chafts

-0.49

rach

-0.49

 pirata

-0.48

 kanyang

-0.47

 argint

-0.47

בור

-0.47

POSITIVE LOGITS

 مرئيه

0.67

__':

0.66

__":

0.64

 pinulongan

0.63

wapV

0.60

XmlAccessType

0.59

Референце

0.59

 esternos

0.58

 مشين

0.58

RenderAtEndOf

0.57

Activations Density 2.991%