INDEX

Explanations

Osaka

The neuron detects proper nouns—especially Japanese place, organization, and personal names.

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

our

-1.48

 ใหญ่

-1.22

GRAFÍA

-1.13

 แต่ง

-1.12

 表情

-1.06

 อาหาร

-1.05

 gravidanza

-1.05

wendi

-1.05

 sembl

-1.05

our

-1.05

POSITIVE LOGITS

1.45

*/

1.25

){

1.21

StoryboardSegue

1.16

езда

1.14

();?>

1.13

knecht

1.12

 JAXBElement

1.11

 įsi

1.11

Activations Density 0.070%