INDEX

Explanations

structural characters and separators

this neuron fires on numeric tokens that include decimal points (floating-point numbers).

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

of

-1.64

 such

-1.47

-1.39

-1.27

-1.26

 pełni

-1.25

-1.23

 sạc

-1.23

 nowo

-1.20

 that

-1.20

POSITIVE LOGITS

 استفاده

1.80

 konserv

1.61

 kategor

1.56

туру

1.54

——————

1.51

 kamera

1.51

 использования

1.48

 tortura

1.45

 etik

1.45

你

1.44

Activations Density 0.194%