INDEX

Explanations

programming examples and legal filings

The neuron strongly fires on the exact word “same.”

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

to

-1.51

for

-1.47

 first

-1.41

 from

-1.31

on

-1.29

has

-1.26

 During

-1.24

 его

-1.20

 other

-1.20

 While

-1.19

POSITIVE LOGITS

憷

1.22



1.20

毟

1.20

conducted

1.18

launched

1.17

 oeil

1.15

1.14

 tornillos

1.13

kinda

1.13

decided

1.13

Activations Density 0.000%