INDEX

Explanations

location prepositions

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

two

-1.75

 with

-1.40

and

-1.38

one

-1.30

or

-1.29

 when

-1.28

 that

-1.27

 same

-1.21

 after

-1.18

 should

-1.13

POSITIVE LOGITS

 throughout

1.68

throughout

1.50

 frigo

1.24



1.20

 astu

1.20

 savon

1.17

 brune

1.16

 camion

1.14

 pantalon

1.13

 poulet

1.13

Activations Density 0.043%