INDEX

Explanations

words often followed by 'is'

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

 this

-1.77

 which

-1.59

 during

-1.54

 until

-1.42

 before

-1.41

 their

-1.34

 some

-1.33

 from

-1.32

 despite

-1.22

as

-1.16

POSITIVE LOGITS

is

1.46

 ไม่มี

1.38

 also

1.36

は

1.36

는

1.25

was

1.22

 همچنین

1.14

 decidedly

1.13

vores

1.10

hh

1.09

Activations Density 0.048%