INDEX

Explanations

parking spaces

The neuron strongly activates on document headings or section titles (the large, often uppercase or prominently formatted labels that introduce new sections).

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

 rowspan

-1.64

:'',

-1.48

 crochê

-1.45

 linho

-1.38

 اپنے

-1.34

 posibilidades

-1.33

itária

-1.29

汌

-1.28

шой

-1.26

étape

-1.23

POSITIVE LOGITS

 parking

1.86

on

1.62

for

1.57

ᴮ

1.42

if

1.29

at

1.27

 automóvil

1.20

 bataille

1.17

 garage

1.16

фильм

1.16

Activations Density 0.023%