INDEX

Explanations

The neuron is a detector for numeric tokens, i.e. pieces of numbers, percentages, or other digits in the text.

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 profondeur

0.56

 สืบค้น

0.55

万美元

0.55

 あり

0.55

getBounding

0.54

擁有

0.54

 jelen

0.54

 फाइनेंशियल

0.54

κτή

0.53

具备

0.52

POSITIVE LOGITS

 goes

1.61

goes

1.40

 allocated

1.38

 Goes

1.34

 spent

1.33

分配

1.23

spent

1.23

 devoted

1.20

 went

1.16

allocated

1.15

Activations Density 0.615%