INDEX

Explanations

I followed by past actions

The neuron responds to the use of the first‐person singular pronoun “I.”

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

 these

-1.82

 THESE

-1.70

is

-1.69

 ezek

-1.57

 Füßen

-1.53

AND

-1.50

ㅡ

-1.50

(?)

-1.48

And

-1.45

․

-1.45

POSITIVE LOGITS

 instead

1.67

 followed

1.50

 then

1.45

at

1.45



1.42

to

1.41

 along

1.37

 stück

1.34

by

1.34

 devoid

1.34

Activations Density 0.042%