INDEX

Explanations

this followed by publication

The neuron primarily fires on the demonstrative pronoun “this.”

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

-1.73

-1.55

in

-1.42

ers

-1.40

',

-1.36

 only

-1.31

to

-1.27

 filha

-1.27

 best

-1.24

-1.23

POSITIVE LOGITS

 tirantes

1.66

 puisse

1.52

 hombros

1.50

嗵

1.41

閹

1.40

劊

1.38

or

1.36

หรือ

1.35

 damski

1.34

decisions

1.33

Activations Density 0.063%