INDEX

Explanations

relative measures

The neuron strongly activates on the word “relative” when it appears as an adjective before another noun (e.g. “relative motion,” “relative positions,” “relative importance,” etc.).

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

ynı

-1.67

鏍

-1.52



-1.51

 zwykle

-1.50

 membag

-1.49

You

-1.45

牴

-1.43

驀

-1.41

vedades

-1.41

 zufried

-1.41

POSITIVE LOGITS

↵

1.84

relative

1.60

在自己

1.49

甃

1.42

到底是

1.41

 ambayo

1.28

only

1.27

 केवल

1.23

并没有

1.22

que

1.21

Activations Density 0.037%