INDEX

Explanations

code snippets and technical terms

The neuron is triggered by colon characters (:) serving as separators or punctuation.

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

The

-1.91

to

-1.87

We

-1.76

of

-1.70

These

-1.70

 They

-1.62

 These

-1.60

PORARY

-1.57

であろう

-1.55

iliki

-1.53

POSITIVE LOGITS

↵

2.27

</h4>

2.11

۔

1.98

牁

1.94

‌.

1.93

espół

1.88

 новые

1.86

 málo

1.84

 lámpara

1.83

 těch

1.82

Activations Density 0.172%