INDEX

Explanations

after, half, over, in, all, best, around

The neuron flags adverbial intensifiers and quantifiers (e.g. “just,” “only,” “over,” “last,” “across,” “one”) that emphasize degree or amount.

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

서

0.60

mmmm

0.59

 সাথে

0.58

υτό

0.55

jenigen

0.52

 всі

0.50

跶

0.50

 vše

0.49

дается

0.49

💕

0.48

POSITIVE LOGITS

0.68

shoring

0.43

ۀ

0.43

-,

0.42

র্জাতিক

0.42

曾在

0.42

 ขณะ

0.40

lings

0.40

dated

0.40

 tangible

0.40

Activations Density 0.000%