INDEX

Explanations

code artifacts

The neuron is looking for numeric literal tokens.

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

İN

-1.38

 Gehir

-1.27

 cantora

-1.25

 cordón

-1.23

İM

-1.20

amkeit

-1.20

 tega

-1.16

便捷

-1.15

 исполь

-1.11

一旁的

-1.10

POSITIVE LOGITS

 these

1.39

这些

1.24

那些

1.11

 such

1.09

 häufig

1.05

 جدًا

1.05

رأة

1.02

 those

1.02

 része

1.02

🤬

1.01

Activations Density 0.002%