INDEX

Explanations

Slavic and Turkish surnames

The neuron is primarily activated by personal names (proper nouns referring to people).

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

 тільки

-1.32

Истори

-1.24

 かわいい

-1.23

 только

-1.22

맏

-1.21

GIR

-1.20

Já

-1.20

 mentales

-1.18

 оригі

-1.15

 більше

-1.14

POSITIVE LOGITS

 costuras

1.39

Welp

1.34

"));

1.28

 forthcoming

1.22

 that

1.21

。"

1.21

 neumáticos

1.20

 том

1.20

 باسلام

1.20

”？

1.19

Activations Density 0.088%