INDEX

Explanations

intensity and degree

The neuron fires on adjectives and adverbs that convey the degree or intensity of something (e.g. strong, intense, marked, large, high, weak).

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

 than

-1.66

 皇族

-1.59

while

-1.48

栒

-1.47

providedIn

-1.42

дів

-1.42



-1.41

бую

-1.38

 passend

-1.36

漉

-1.35

POSITIVE LOGITS

っぱり

1.65

 několik

1.39

 такая

1.39

 หลัง

1.35

 Both

1.30

</em>

1.29

兩

1.25

);

1.23

ませんでした

1.23

 コピー

1.22

Activations Density 0.181%