INDEX

Explanations

personal pronouns, names, or "the"

This neuron lights up on first‐person subject phrases (like “I …” or “We …”) that introduce personal statements or actions.

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

 also

-1.56

 también

-1.52

 também

-1.50

 גם

-1.49

 También

-1.38

ઃ

-1.38

therefore

-1.36

 zudem

-1.36

 then

-1.34

Также

-1.34

POSITIVE LOGITS

1.52

 first

1.50

 actually

1.43

1.27

 definitely

1.22

 mostly

1.21

 started

1.16

has

1.16

is

1.15

 very

1.14

Activations Density 0.038%