INDEX

Explanations

code syntax

This neuron detects floating‐point numeric literals (numbers with decimal points) in code.

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

its

-1.79

the

-1.63

稣

-1.30

 lesquels

-1.23

Its

-1.20

牠

-1.20

ramid

-1.20

Our

-1.16

相应的

-1.16

 their

-1.15

POSITIVE LOGITS

1.52

 albeit

1.46

也有

1.39

也是

1.38

rscheinlich

1.28

特に

1.25

");

1.24

虽然

1.22

 هذا

1.21

 melalui

1.20

Activations Density 0.015%