INDEX

Explanations

list separators

The neuron activates on numeric data—years, statistics, and other numbers—whenever they appear 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

Negative Logits

 although

1.35

 aunque

1.27

 जबकि

1.25

 pero

1.20

 लेकिन

1.20

 tetapi

1.18

 wobei

1.16

 yaitu

1.15

 nhưng

1.13

 પરંતુ

1.13

POSITIVE LOGITS

0.66

の

0.55

/*/

0.54

 themselves

0.51

IFIED

0.50

ۗ

0.50

 ใด

0.50

 abroad

0.49

)));

0.48

Activations Density 0.173%