INDEX

Explanations

computer code

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

########.

-0.79

ьаж

-0.79

 cherchés

-0.76

Hentet

-0.76

AxisAlignment

-0.73

تقاوى

-0.73

 defaultstate

-0.72

AndEndTag

-0.69

 StatefulWidget

-0.67

NameInMap

-0.66

POSITIVE LOGITS

wapV

0.51

UGU

0.47

HAM

0.47

 lagu

0.45

ta

0.44

汰

0.43

pla

0.43

oton

0.42

ugu

0.42

ham

0.41

Activations Density 0.248%