INDEX

Explanations

age, kind, generation, class, caliber

The neuron detects mentions of a person’s age or generational reference (e.g. “age,” “generation”).

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

两位

-1.36

ẵn

-1.28

two

-1.26

 Arxivat

-1.22

ulitis

-1.20

ætter

-1.19

ETRIC

-1.18

↵↵

-1.17

AMENTE

-1.17

hæng

-1.16

POSITIVE LOGITS

1.80

1.61

1.57

or

1.53

1.48

</strong>

1.41

 halen

1.39

omst

1.29

Activations Density 0.031%