INDEX

Explanations

religious concepts and questions

This neuron detects mentions of Jesus (or explicit Christian salvation language).

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

or

-1.46

so

-1.34

 both

-1.32

 from

-1.21

two

-1.20

 after

-1.18

 either

-1.17

 always

-1.10

 hendak

-1.09

客戶

-1.07

POSITIVE LOGITS

 این

1.20

írez

1.19

Neden

1.14

Besos

1.11

дження

1.10

bildet

1.10

 réglementation

1.09

 قبل

1.07

 Holistic

1.07

ではありません

1.05

Activations Density 0.000%