INDEX

Explanations

greetings and positive exclamations

This neuron activates on greeting or introductory phrases (e.g. “Welcome to…,” “Let’s…”) that open a document.

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

리지

0.79

就不会

0.74

더라도

0.73

就好了

0.70

라도

0.67

此事

0.63

LocalizedString

0.63

விட்டால்

0.62

 heard

0.61

лно

0.61

POSITIVE LOGITS

 👋

1.01

!...

0.97

!,

0.93

!-

0.91

!.

0.87

👋

0.86

!;

0.85

oor

0.83

!..

0.81

 karşınız

0.78

Activations Density 0.346%