INDEX

Explanations

finding a way

The neuron strongly activates on the word “way,” marking occurrences of that exact token.

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

you

-2.67

 outras

-2.52

 другие

-2.47

 otras

-2.22

 autre

-2.14

 другое

-2.08



-2.06

 другими

-2.05

 pressing

-1.98

other

-1.97

POSITIVE LOGITS

2.89

2.78

2.72

2.70

ra

2.44

own

2.42

2.38

2.33

嫱

2.17

一些

2.16

Activations Density 0.004%