INDEX

Explanations

medical, social, and organizational entities

The neuron detects nouns that are specific entities like places, institutions, medical conditions, or technical objects.

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

 zout

-1.63

 vandens

-1.42

to

-1.40

 geel

-1.36

も多く

-1.34

 неё

-1.34

着一个

-1.34

 gyvento

-1.31

場合には

-1.31

 hvit

-1.30

POSITIVE LOGITS

 from

1.90

 their

1.74

you

1.63

From

1.60

 от

1.56

With

1.53

 desde

1.52

 даже

1.52

 их

1.51

One

1.50

Activations Density 0.335%