INDEX

Explanations

dimension values like px and em

This neuron detects numeric literals (e.g. measurement values) in 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

 dynamis

-1.23

it

-1.21

why

-1.20

APOR

-1.20

 rotación

-1.19

què

-1.18

 flexibilidad

-1.16

ངས་

-1.16

日閲覧

-1.16

 сейчас

-1.16

POSITIVE LOGITS

 again

1.56

 دوباره

1.35

lierung

1.22

總是

1.22

块钱

1.11

felizmente

1.10

 цьому

1.09

CGRectMake

1.09

 edges

1.09

mountable

1.09

Activations Density 0.016%