INDEX

Explanations

larger, higher, supérieur

The neuron activates on numeric tokens and numeric expressions (e.g., multi-digit numbers and decimals), i.e. it detects mentions of numerical values.

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

低

1.31

 smaller

1.29

 rendah

1.27

ต่ำ

1.27

 Smaller

1.26

 diminutive

1.23

low

1.22

 صغير

1.22

Smaller

1.20

 kleiner

1.18

POSITIVE LOGITS

 higher

1.37

higher

1.32

Higher

1.27

 höheren

1.24

 Higher

1.23

 höher

1.20

 yüksek

1.19

超出

1.18

 höhere

1.18

 hoger

1.15

Activations Density 0.995%