INDEX

Explanations

years and dates

The neuron activates on four-digit numbers representing years or dates.

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

});*/

-1.37

 vêtement

-1.36

atória

-1.32

 kveld

-1.28

⅗

-1.27

 emballage

-1.25

 zgodnie

-1.25

 rød

-1.24

 payé

-1.21

 vider

-1.19

POSITIVE LOGITS

了不少

1.33

了许多

1.25

了一些

1.14

了些

1.13

and

1.13

 edilen

1.11

了很多

1.09

了两

1.04

 tyto

1.04

to

1.02

Activations Density 0.117%