INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

who

-2.38

 have

-1.80

 whom

-1.68

its

-1.63

-1.48

 includes

-1.45

 cannot

-1.45

 whose

-1.45

 because

-1.43

 поскольку

-1.41

POSITIVE LOGITS

 บาง

1.79

these

1.73

Especially

1.72

those

1.69

xvii

1.63

 majeurs

1.60

 واقعا

1.56

Definitely

1.54

 extérieurs

1.53

ſtra

1.52

Activations Density 0.000%

No Known Activations

This feature has no known activations.