INDEX

Explanations

definitions and introductions

The neuron activates on numeric tokens (digits, numbers, and numeric literals).

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

 paixão

-1.26

 estadia

-1.16

 لأنه

-1.11

 ἐν

-1.09

Sábado

-1.09

 وكانت

-1.08

gulama

-1.06

⬘

-1.05

 cinza

-1.04

 trilha

-1.04

POSITIVE LOGITS

 will

1.51

 from

1.46

if

1.34

of

1.10

 daca

1.07

ую

1.02

 результат

1.00

 with

0.98

 apartament

0.97

 fald

0.95

Activations Density 0.007%