INDEX

Explanations

election polls

This neuron detects numeric and statistical data in text, especially poll results, percentages, and other numbers.

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

ׇ

-1.72

 گیاه

-1.30

 النبات

-1.25

:{

-1.19

 hör

-1.17

 растение

-1.13

statechange

-1.13

herstellung

-1.11

 вещества

-1.09

'},

-1.09

POSITIVE LOGITS

ֵּ

2.05

ִּ

1.70

ַּ

1.59

ּוֹ

1.54

ֶּ

1.52

にほんブログ村

1.48

ではでは

1.41

 птиц

1.38

 bagus

1.38

ְּ

1.36

Activations Density 0.019%