INDEX

Explanations

names of people

The neuron flags occurrences of personal names (proper nouns referring to people).

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

in

-1.33

читайте

-1.30

езда

-1.26

 inmigrantes

-1.16

 Igreja

-1.05

 gimnasio

-1.05

iddler

-1.05

лите

-1.05

手镯

-1.03

Colm

-1.02

POSITIVE LOGITS

</h2>

1.45

número

1.27

 сьогодні

1.23

lepší

1.15

/>}

1.12

 other

1.10

</h1>

1.10

 něj

1.09

َل

1.09

[]:

1.08

Activations Density 0.091%