INDEX

Explanations

file path and network endpoint parameters

This neuron detects floating-point numeric literals (decimal numbers) in code.

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 these

-1.98

 this

-1.78

not

-1.52

 when

-1.41

by

-1.16

 این

-1.09

 vayan

-1.06

っていたので

-1.06

 этой

-1.05

-1.02

POSITIVE LOGITS

Elaboración

1.73

DESCRIPCIÓN

1.51

Preparación

1.35

Outros

1.33

|}{\

1.31

 également

1.24

Definición

1.24

owment

1.23

That

1.23

Leírás

1.22

Activations Density 0.010%