INDEX

Explanations

part of a whole

The neuron fires on words that denote subdivisions or segments—e.g. “point,” “part,” “section,” “line,” “region,” “portion,” or “form.”

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

and

-1.66

不同的

-1.52

 diferite

-1.37

mathrm

-1.28

不同

-1.27

以及

-1.24

 разные

-1.19

oczes

-1.19

 different

-1.17

متن

-1.16

POSITIVE LOGITS

 that

3.36

of

2.17

 which

1.82

 που

1.80

who

1.66

 whose

1.64

you

1.63

 التي

1.59

 where

1.53

 الذي

1.41

Activations Density 0.097%