INDEX

Explanations

titles and lists

The neuron fires on tokens containing non-ASCII or extended Unicode characters (e.g. accented letters, special symbols, or other non-Latin glyphs).

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

-1.63

なこと

-1.56

 POSSIBLE

-1.40



-1.38

 знать

-1.37

 '/':

-1.37

采用了

-1.36

ことが多い

-1.34

气息

-1.34

なんと

-1.30

POSITIVE LOGITS

\}$,

1.52

 آنها

1.42

 gewinnt

1.41

」，

1.39

 additions

1.37

 красивый

1.34

Of

1.34

 klingt

1.32

 newest

1.30

 other

1.27

Activations Density 0.001%