INDEX

Explanations

vector bundle and covering

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

 scolaires

-0.77

 главе

-0.75

 поса

-0.73

એ

-0.71

治

-0.71

ễm

-0.68

ň

-0.68

ówek

-0.68

fcntl

-0.68

 وأ

-0.68

POSITIVE LOGITS

 covering

1.29

 Covering

1.15

 coverings

1.05

 fibers

0.95

 fiber

0.93

covering

0.91

fiber

0.90

fib

0.89

 bundle

0.88

 Fiber

0.88

Activations Density 0.044%