INDEX

Explanations

entries, songs, and abstracts

The neuron fires on named‐entity tokens—proper names of people, organizations, events, places, and dates.

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

或者

-1.46

or

-1.40

 autre

-1.38

 opinie

-1.37

you

-1.30

因为

-1.30

 karena

-1.30

 også

-1.28

 hoặc

-1.28

 ayakkab

-1.25

POSITIVE LOGITS

 distinguishes

1.35

 precis

1.34

 Eurovision

1.32

дёт

1.31

 concierto

1.23

 fascin

1.22

 Siehe

1.21

 symbolizes

1.20

 fora

1.20

 difer

1.19

Activations Density 0.019%