INDEX

Explanations

The neuron activates on numeric literals (i.e. tokens that are numbers or digits).

programming code snippets

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

 with

-1.30

 like

-1.24

to

-1.21

one

-1.13

by

-1.11

of

-1.08

lampu

-1.02

сам

-1.01

how

-1.01

tros

-0.98

POSITIVE LOGITS

atized

1.20

满脸

1.17

艄

1.16

ěř

1.13

ensitive

1.11

ulence

1.11

dienne

1.10

olving

1.10

终究

1.10

rsquo

1.09

Activations Density 0.039%