INDEX

Explanations

choosing or selecting options

This neuron activates on words meaning “to choose” or “to select” (e.g. select, choose, pick, etc.).

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

↵

-2.64

{\

-2.08

//

-2.05

是一個

-2.03

 letz

-1.98

いわゆる

-1.95

孭

-1.93

 Those

-1.92

喼

-1.91

POSITIVE LOGITS

༛

2.61

 唯美

2.47

 cliquer

2.45



2.45

 malé

2.44

 ajouter

2.38

谖

2.34

 maniere

2.33

迓

2.30

 réessayer

2.27

Activations Density 0.002%