INDEX

Explanations

dates with numbers

The neuron primarily detects numeric characters (digits), especially those occurring in years and other numbers.

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



-1.36

也

-1.35

这些

-1.27

枼

-1.27

这

-1.27

 nowej

-1.27

也會

-1.24

 nowego

-1.23

Selain

-1.23

 Coupled

-1.22

POSITIVE LOGITS

to

1.30

it

1.24

 with

1.23

áctico

1.22

报表

1.15

zielle

1.14

kya

1.12

its

1.11

 before

1.10

 within

1.10

Activations Density 0.306%