INDEX

Explanations

possessive pronouns

The neuron fires on possessive pronouns (e.g. “their,” “your,” “his”).

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

 egent

-1.58

which

-1.58

多くの

-1.57

只要

-1.53

minded

-1.51

-1.50

 bilder

-1.48

主要

-1.47

-1.46

 egens

-1.45

POSITIVE LOGITS

</h2>

2.63

área

1.56

捋

1.55

⬈

1.48

 senhora

1.48

羮

1.44

to

1.41

 τῶν

1.39

 También

1.38

Activations Density 0.012%