INDEX

Explanations

topic of

The neuron activates on the head nouns in “X of Y” constructions (e.g. “power,” “boundaries,” “load,” “limits,” and especially the preposition “of”).

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

 there

-2.27

 these

-1.90

 time

-1.60

 also

-1.56

 altså

-1.55

Ḍ

-1.55

oudoune

-1.53

but

-1.49

稳定的

-1.47

ặp

-1.42

POSITIVE LOGITS

os

1.95

of

1.88

aży

1.72

 swojej

1.72

based

1.68

 своей

1.65

 купить

1.61

1.59

 swoim

1.58

 kysy

1.58

Activations Density 0.129%