INDEX

Explanations

question and code beginnings

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

我們的

-1.22

 Ejército

-1.19

źródło

-1.16

besos

-1.16

Funktionen

-1.16

for

-1.16

 higiene

-1.14

laşı

-1.13

蛻

-1.12

 varandra

-1.11

POSITIVE LOGITS

‘

1.41

了些

1.19

readFileSync

1.13

＇

1.13

他也

1.10

}\}$

1.10

 beziehungs

1.06

 …..

1.06

should

1.05

him

1.03

Activations Density 0.014%