INDEX

Explanations

calamities and widespread suffering

The main thing this neuron does is detect mentions of large‐scale catastrophes—such as famines, plagues, epidemics, and other major disasters.

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

ৢ

-1.64

नलोड

-1.52



-1.49

 tarefas

-1.47

ayer

-1.43

 lixo

-1.42

 イラスト

-1.41

 například

-1.39

 včetně

-1.39

 entanto

-1.38

POSITIVE LOGITS

it

1.76

太大

1.28

ترین

1.20

ቷ

1.20

就會

1.18

 feine

1.14

 Munic

1.14

 Massive

1.13

ające

1.13

 rusa

1.10

Activations Density 0.087%