INDEX

Explanations

is a or are

The neuron fires strongly on numeric tokens (especially measurements with digits and decimal points).

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

on

-1.42

it

-1.41

mathrm

-1.38

 Because

-1.34

сные

-1.31

堉

-1.31

 pelatihan

-1.30

 then

-1.29

 with

-1.27

 групи

-1.24

POSITIVE LOGITS

})

1.66

wants

1.48

}))

1.46

 mahdol

1.45

seemed

1.44

EdgeInsets

1.43

神

1.43

了一个

1.43

began

1.42

一段时间

1.42

Activations Density 0.151%