INDEX

Explanations

html tags and structure

The neuron is detecting runs of leading whitespace used for indentation in markup.

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

 toneladas

-1.08

 this

-1.08

 informar

-1.06

скажите

-1.06

ровка

-1.04

Ży

-1.03

 completas

-1.01

んですよ

-0.99

cended

-0.98

 rokov

-0.95

POSITIVE LOGITS

2.06

1.94

1.77

"><

1.70

'><

1.48

 hierfür

1.43

><

1.27

$<

1.17

;<

1.16

$<$

1.12

Activations Density 0.016%