INDEX

Explanations

closing parentheses or code blocks

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Trigger

1.22

प्प

1.22

 TRIGGER

1.19

ж

1.17

дат

1.14

鵠

1.12

vu

1.08

ventyConfig

1.08

す

1.08

\"

1.08

POSITIVE LOGITS

gzip

1.78

 gzip

1.74

 ribbon

1.65

转换

1.64

 пище

1.60

 przyję

1.59

skinned

1.57

decomposition

1.57

revalidator

1.57

 acond

1.54

Activations Density 0.058%