INDEX

Explanations

news headlines and titles

This neuron detects XML attribute tokens (especially Android “android:…” attributes and their state/value names) in resource/selector files.

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

 into

-1.18

zels

-1.11

 detalló

-1.08

onymes

-1.07

ﻖ

-1.05

教训

-1.05

 ideas

-1.03

way

-1.02

 τρό

-1.02

այի

-1.01

POSITIVE LOGITS

᱐

1.00

 chré

0.94

0.92

nef

0.91

濆

0.90

/*@

0.87

外部链接

0.86

 कहा

0.85

 هیچ

0.85

immel

0.85

Activations Density 0.004%