INDEX

Explanations

bi- words

The neuron fires on the hyphenated technical term “bi-directional.”

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

↵↵

-3.05

-2.77

 worin

-2.47

ha

-2.41

—

-2.31

‘

-2.22

-2.19

’

-2.03

 yaklaşık

-2.03

 использу

-1.98

POSITIVE LOGITS

2.75

 dekoratif

2.45

 elektrik

2.39

оргаш

2.36

 aksesuar

2.31

⢊

2.22

Rumah

2.20

 etek

2.19

 organik

2.16

 abiye

2.13

Activations Density 0.029%