INDEX

Explanations

wheeled devices and carts

The neuron detects mentions of wheels or wheeled devices (e.g. “wheel,” “wheels,” “wheeled,” “casters,” “rollers”).

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

↵

-1.53

-1.37

falls

-1.30

 however

-1.29

for

-1.20

 year

-1.16

solver

-1.16

year

-1.16

product

-1.14

of

-1.13

POSITIVE LOGITS

Gilla

1.45

 wheelchairs

1.40

轱

1.36

 卧室

1.35

 tirantes

1.33

 jiné

1.32

panasonic

1.30

niosek

1.26

 jsme

1.24

 厂家

1.24

Activations Density 0.071%