INDEX

Explanations

shooting

The neuron primarily activates on occurrences of the word “shooting.”

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

-4.25

是

-3.78

价格

-2.58

!!!!!!!!

-2.48

ｓ

-2.47

-2.45

 leur

-2.42

 atau

-2.41

 extranjeros

-2.39

所有

-2.36

POSITIVE LOGITS

趼

3.16

觏

2.98

姈

2.95

 vollständ

2.89

 waarschijnlijk

2.73

阄

2.73

 causando

2.67

Ꭳ

2.66

を与

2.58

みたいです

2.55

Activations Density 0.003%