INDEX

Explanations

words indicate timing or sequence

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

 both

-1.27

 what

-1.26

μένα

-1.14

cargas

-1.13

any

-1.12

と言えば

-1.09

 пыта

-1.09

 mejorar

-1.09

ständige

-1.08

furl

-1.07

POSITIVE LOGITS

 only

1.62

只

1.37

complished

1.30

 last

1.27

 early

1.18

 after

1.16

 until

1.16

 فقط

1.15

 starting

1.14

 AQUÍ

1.14

Activations Density 0.070%