INDEX

Explanations

fields like firstname, lastname, hostname

The neuron activates on occurrences of “firstname” and “lastname” (and variations thereof) in code or data.

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

孥

-3.27

籥

-2.86

 большим

-2.56

懨

-2.55

 biografias

-2.47

 become

-2.41

 χρησιμοποι

-2.34

黩

-2.33

 έχουν

-2.28

 Второй

-2.28

POSITIVE LOGITS

 Then

2.67

2.34

恫

2.31

ly

2.30

 Finally

2.27

 Meanwhile

2.19

le

2.19

2.14

 Instead

2.11

Activations Density 0.002%