INDEX

Explanations

specified Incomplete types

This neuron detects standalone numeric literals (tokens containing digits) in code or text.

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

-1.34

is

-1.21

of

-1.20

by

-1.11

 from

-1.07

-1.01

 This

-1.00

 tecnologias

-0.97

 this

-0.97

POSITIVE LOGITS

臬

1.16

Вопрос

1.13

 échanti

1.08

Daniele

1.08

Прода

1.08

KURZ

1.07

Отлич

1.06



1.06

名单

1.05

Подробнее

1.05

Activations Density 0.023%