INDEX

Explanations

construction and contractors

The neuron fires on the very first token of a paragraph or block (i.e. it marks paragraph beginnings).

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

 стекла

-0.91

 verrou

-0.86

etched

-0.86

ственная

-0.86

çuk

-0.84

 caucho

-0.83

ప్ర

-0.83

partimento

-0.82

laß

-0.81

Cheese

-0.79

POSITIVE LOGITS

 construction

3.66

 Construction

3.03

 contractors

2.84

construction

2.83

 contractor

2.81

Construction

2.78

 builders

2.67

 builder

2.53

 CONSTRUCTION

2.38

 строи

2.34

Activations Density 0.122%