INDEX

Explanations

doing an action

The neuron detects mentions of a facial expression—phrases describing someone’s “look” of an emotion (e.g. “a confused look of mine”).

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

-1.68

both

-1.39

 perchè

-1.37

demic

-1.37

though

-1.34

-1.33

 leſs

-1.32

 isShow

-1.29

-1.28

 azzurro

-1.27

POSITIVE LOGITS

 pediu

1.23

我們的

1.23

präch

1.19

过来了

1.19

してない

1.19

Ár

1.18

 perdeu

1.14

 iria

1.14

られています

1.13

できない

1.13

Activations Density 0.003%