INDEX

Explanations

quantities and durations

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

or

-1.42

 three

-1.39

 five

-1.30

six

-1.22

two

-1.21

 while

-1.19

 four

-1.18

at

-1.14

 nine

-1.08

 eight

-1.06

POSITIVE LOGITS

several

1.60

 plusieurs

1.52

 vários

1.42

 flera

1.32

 چند

1.26

 várias

1.25

 여러

1.19

 कई

1.19

hundreds

1.13

 нескольких

1.10

Activations Density 0.111%