INDEX

Explanations

Democratic politicians and elections

The main thing this neuron does is identify trigonometric function names (e.g., sin, cos, cot, csc) in mathematical expressions.

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

 begleitet

-1.30

بدأ

-1.30

тивные

-1.27

というわけで

-1.27

élène

-1.25

it

-1.24

auto

-1.24

 betrifft

-1.23

ाप्त

-1.22

 convertido

-1.22

POSITIVE LOGITS

 getP

1.55

 Uniwers

1.53

⇡

1.52

 SimpleName

1.51

 nabo

1.43

 freak

1.42

 geburtstag

1.40

 概要

1.40

wreck

1.40

сії

1.40

Activations Density 0.121%