INDEX

Explanations

course, recipes, classical, factories, patient

The neuron fires whenever it encounters numeric or quantified information (numbers with units, counts, measurements, durations, etc.).

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

we

-1.34

our

-1.34

 réjou

-1.27

 навіть

-1.27

Then

-1.26

 éte

-1.23

 relâche

-1.16

 célè

-1.16

layın

-1.15

 démission

-1.15

POSITIVE LOGITS

 with

1.56

and

1.38

 also

1.27

 primarily

1.16

for

1.16

in

1.15

 received

1.15

 gradually

1.14

 reportedly

1.10

 provide

1.09

Activations Density 0.048%