INDEX

Explanations

font and font-related terms

The neuron activates on occurrences of “font” (or “fonts”)—in names, identifiers, and declarations—i.e. it flags any token related to font references.

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

呖

-3.30

vantaged

-2.98

of

-2.95

on

-2.94

 باسلام

-2.78

NESSEE

-2.52

żli

-2.30

ia

-2.28

轳

-2.27

ی

-2.23

POSITIVE LOGITS

Ꮉ

2.70

經常

2.66

 SOME

2.44

 célè

2.42

 mať

2.42

諼

2.39

 باستخدام

2.38

喜歡的

2.34

秕

2.31

 OGSÅ

2.30

Activations Density 0.007%