INDEX

Explanations

Hon. titles or names

The neuron detects formal honorifics and titles (e.g. “Hon.”, “Sir”, “Mr”, “Lord”, “Lady”) that precede or style a person’s name.

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

 muhte

-1.34

 ausein

-1.32

 prachtige

-1.32

bilisi

-1.30

 másik

-1.30

 they

-1.29

 gyer

-1.26

meneu

-1.26

 görmek

-1.25

lossen

-1.24

POSITIVE LOGITS

1.42

an

1.27

<i>

1.21

1.20

 gennem

1.17

1.16

 nearly

1.16

 हुए

1.12

 incendio

1.11

 while

1.09

Activations Density 0.039%