INDEX

Explanations

words "finite" and "infinite," as well as "interpret" and its inflections

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

No Comments

Negative Logits

 infinite

-1.34

<bos>

-1.20

infinite

-1.13

 Infinite

-1.06

 unlimited

-0.99

Infinite

-0.96

 infinita

-0.90

 infinito

-0.88

 infinity

-0.82

 limitless

-0.81

POSITIVE LOGITS

وردار

0.54

سمبر

0.54

pecha

0.50

 découvertes

0.49

 Pyle

0.49

tually

0.47

?',

0.47

),

0.47

Obrázky

0.46

ture

0.46

Activations Density 0.920%