INDEX

Explanations

word endings

The main thing this neuron does is detect numeric tokens or numerical values (e.g., integers, decimals, codes).

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

们

0.41

могою

0.40

олові

0.40

чением

0.39

ުޅ

0.38

燚

0.38

νοντας

0.38

acelet

0.38

роки

0.37

ERATE

0.37

POSITIVE LOGITS

 kommen

0.40

0.39

 tien

0.39

es

0.38

 nessun

0.38

 have

0.38

 hanno

0.38

 plaats

0.38

zes

0.37

 têm

0.37

Activations Density 0.008%