INDEX

Explanations

areas and regions

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

᾿

-1.15

 sapatos

-1.14

 vilken

-1.10

gisayar

-1.08

 LoggerFactory

-1.07

 totaal

-1.04

who

-1.04

 objectMapper

-1.03

 deportivas

-1.02

 الذي

-1.02

POSITIVE LOGITS

 such

1.96

 areas

1.65

 namely

1.27

 like

1.26

 regions

1.22

of

1.18

such

1.15

 یعنی

1.11

之一

1.11

 таких

1.10

Activations Density 0.113%