INDEX

Explanations

keys followed by colon

This neuron detects numeric literals (numbers) in code or configuration snippets.

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

已是

-1.23

娣

-1.23

 prípade

-1.22

蛱

-1.22

brill

-1.17

 into

-1.16

satunya

-1.15

到底是

-1.14

indes

-1.14

 Američ

-1.13

POSITIVE LOGITS

1.66

 llorar

1.25

1.20

潜力

1.20

}=\

1.15

riller

1.14

></

1.11

 británico

1.10

küche

1.09

遼

1.09

Activations Density 0.042%