INDEX

Explanations

tech companies and services

The neuron fires on the names of web mapping/data‐service providers (e.g. “baidu,” “google,” “高德,” etc.).

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

我们

-1.78

在我

-1.74

但是

-1.67

The

-1.66

 errori

-1.61

 beeind

-1.57

世界

-1.55

 dergleichen

-1.52

 tanpa

-1.48

 ยัง

-1.48

POSITIVE LOGITS

are

1.91

↵↵

1.55

1.52

⡪

1.51

’

1.45

 martin

1.29

and

1.29

arv

1.29

of

1.28

Activations Density 0.013%