INDEX

Explanations

restaurant or establishment

The neuron specializes in spotting named entities—proper nouns such as restaurant, venue, film, and person names.

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

 hırka

-1.59

 komik

-1.53

 harita

-1.51

 yelek

-1.51

妧

-1.45



-1.43

approximately

-1.40

barkeit

-1.39

 triko

-1.38

 diki

-1.37

POSITIVE LOGITS

in

1.93

by

1.90

 when

1.48

at

1.46

 with

1.45

 showing

1.43

no

1.43

all

1.42

 where

1.41

 without

1.38

Activations Density 0.025%