INDEX

Explanations

heraldic symbols and colors

The neuron detects heraldic or coat‐of‐arms terminology and descriptions.

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

to

-1.63

-1.50

 then

-1.49

っていた

-1.42

 especially

-1.42

 there

-1.40

 protože

-1.39

 time

-1.38

},

-1.37

 nhung

-1.37

POSITIVE LOGITS

民众

1.27

Zapraszamy

1.23

 menace

1.20

Pengertian

1.19

さてさて

1.18

试验

1.17

设施

1.15

爱好

1.14

 Nedir

1.11

ogues

1.11

Activations Density 0.029%