INDEX

Explanations

"I" followed by past tense verbs

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

are

-1.95

 have

-1.78

Were

-1.17

 will

-1.16

}">

-1.14

 έχουν

-1.06

 Were

-1.05

目前

-1.05

']['

-0.99

do

-0.98

POSITIVE LOGITS

was

2.66

 wasn

1.52

 remember

1.43

 knew

1.36

had

1.30

 doesn

1.27

記得

1.25

 remembers

1.23

 estuviera

1.13

isn

1.11

Activations Density 0.040%