INDEX

Explanations

mathematical functions like ln, sin, cos, sqrt

The neuron detects occurrences of single-argument mathematical function names (like ln, sqrt, cos) in the text.

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

 will

-1.73

one

-1.48

and

-1.45

at

-1.40

caucasian

-1.39

all

-1.32

cartier

-1.31

ℋ

-1.30

use

-1.30

 find

-1.28

POSITIVE LOGITS

 เรา

1.42

 بالإضافة

1.41

 antworte

1.40

rfan

1.40

 خیلی

1.35

really

1.34

www

1.34

should

1.32

igth

1.30

Activations Density 0.079%