INDEX

Explanations

file paths

The neuron flags numeric literal tokens (e.g. integers or floating-point numbers) 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

 monaco

-1.34

自带

-1.21

 barcelona

-1.21

id

-1.16

他会

-1.13

</h1>

-1.13

内置

-1.12

 chante

-1.11

烤

-1.11

逦

-1.10

POSITIVE LOGITS

 był

1.63

 Sementara

1.37

 "'");

1.30

 going

1.26

 what

1.26

)>>

1.23

the

1.23

 była

1.22

 Tinggi

1.22

так

1.20

Activations Density 0.004%