INDEX

Explanations

foreign words and abbreviations

The neuron responds to standalone single‐letter uppercase tokens (e.g. “K,” “M,” “E,” “R”)—typically the isolated capital letters that appear as section headings or byline initials.

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

を

-1.83

で

-1.65

と

-1.57

が

-1.56

そして

-1.55

などの

-1.53

at

-1.50

つまり

-1.44

～～

-1.38

但这

-1.35

POSITIVE LOGITS

為に

1.67

 glisser

1.46

 frança

1.45

齜

1.44

 valentín

1.44

 poderosos

1.44

ようになります

1.41

際は

1.41

 siè

1.41

様な

1.40

Activations Density 0.202%