INDEX

Explanations

first name followed by last name

The neuron activates on personal names, i.e. proper nouns identifying 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

ambut

-1.39

kitab

-1.34

猻

-1.33

تس

-1.33

zdroj

-1.32

acaktır

-1.31



-1.30

 camisetas

-1.30

 medalla

-1.25

 pomys

-1.25

POSITIVE LOGITS

nment

1.53

 chrétienne

1.41

 😭😭

1.34

 множество

1.34

🤧

1.33

 africaine

1.29

 🤣🤣

1.29

 😂😂😂

1.26

😡

1.25

😜

1.22

Activations Density 0.082%