INDEX

Explanations

Dr. Company We noticed

The neuron is detecting numeric literals (numbers, including integers and decimals) in code.

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

 sejam

-1.61

McF

-1.41

razine

-1.37

 trataba

-1.34

轻易

-1.30

⃤

-1.27

を広

-1.27

hauled

-1.23

 podamos

-1.23

chea

-1.22

POSITIVE LOGITS

 nuovo

1.47

 Their

1.41

無い

1.41

どの

1.35

 века

1.32

 bagaimana

1.31

 Wszyst

1.31

 pères

1.28

 кофе

1.27

vertisers

1.26

Activations Density 0.001%