INDEX

Explanations

citations and URLs

The neuron detects numeric tokens—especially percentages, decimal numbers, and similar numerical values.

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

),

-1.30

if

-1.23

すると

-1.23

 longstanding

-1.22

ları

-1.21

 longtime

-1.16

 орден

-1.16

 Even

-1.15

了起来

-1.15

arbeit

-1.14

POSITIVE LOGITS

褙

1.80

1.62

სქ

1.51

窣

1.47

Viitteet

1.45

敺

1.40

 Aufenthal

1.38

 vagas

1.37

cetak

1.35

 jednego

1.32

Activations Density 0.086%