INDEX

Explanations

The neuron primarily activates on numeric tokens, i.e. digits and number sequences.

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

Whilst

1.26

๑

1.13

鰤

1.11

Firstly

1.08

🇮

1.07

🚢

1.07

🥥

1.06

🍘

1.05

🛳

1.03

Про

1.02

POSITIVE LOGITS

 statewide

1.45

 Statewide

1.30

 County

1.30

 Sandusky

1.27

 Danville

1.23

 Oswego

1.22

 Fayette

1.21

 Spokane

1.20

 county

1.17

 Missouri

1.16

Activations Density 6.430%