INDEX

Explanations

recommendations and thanks

The neuron detects exclamation marks (tokens representing “!”), especially repeated or emphatic ones.

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

konos

-1.07

😲

-1.04

😂😂

-1.03

💀

-1.01

🤣🤣

-0.98

farms

-0.96

😡

-0.93

 questo

-0.92

😮

-0.91

 WHEREAS

-0.90

POSITIVE LOGITS

PS

1.28

Again

1.22

ps

1.13

Five

1.10

 Thanks

1.07

 Update

1.04

 Cheers

1.04

five

1.03

PS

1.02

 five

1.02

Activations Density 0.003%