INDEX

Explanations

we followed by a verb

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

 duque

-1.12

 rodilla

-1.11

 gobernador

-1.06

 いた

-1.06

上述

-1.05

we

-1.04

 были

-1.03

 emperador

-1.02

 المياه

-1.02

 есть

-1.00

POSITIVE LOGITS

 then

2.53

 also

1.91

 thereby

1.63

 thus

1.52

 therefore

1.38

 então

1.24

Then

1.17

 hereby

1.16

 następnie

1.13

就能

1.10

Activations Density 0.104%