INDEX

Explanations

various followed by plural nouns

The neuron detects words that denote “other” or “various” items (e.g. その他の, 全, various).

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

他

-1.92

-1.89

↵↵

-1.86

."

-1.84

 lmao

-1.82

 การ

-1.78

eds

-1.74

 longues

-1.73

\\

-1.73

jj

-1.72

POSITIVE LOGITS

 this

2.38

卨

2.30

 staunch

2.28

 noteworthy

2.22

焢

2.17

 estampa

2.16

 multifaceted

2.08

 horrific

2.06

 sizable

2.03

掲示

2.02

Activations Density 0.003%