INDEX

Explanations

public perception

The neuron fires on tokens in passages presenting quantitative or statistical information (numbers, figures, polls, percentages, etc.).

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

 Someone

0.64

Someone

0.61

 someone

0.57

 Geometry

0.54

sometimes

0.54

 촬영

0.54

 Sometimes

0.52

someone

0.52

 geometry

0.52

 sometimes

0.51

POSITIVE LOGITS

民众

2.52

ประชาชน

2.44

 مردم

2.28

 ప్రజ

2.25

 जनता

2.22

 जनते

2.20

 rakyat

2.19

民眾

2.19

 জনগণ

2.16

 citizenry

2.16

Activations Density 0.842%