INDEX

Explanations

events by someone or titled

The neuron detects mention of specific event activities or session types (e.g. tastings, presentations, talks, screenings) in a program listing.

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

 должны

-1.34

 '=',

-1.26

The

-1.24

 olmak

-1.20

 karena

-1.16

It

-1.16

的

-1.16

),

-1.16

冬

-1.15

twimg

-1.14

POSITIVE LOGITS

by

1.62

 between

1.36

 juſ

1.25

 about

1.20

чних

1.19

 from

1.19

 décès

1.19

 with

1.18

 before

1.18

 eſſ

1.16

Activations Density 0.063%