INDEX

Explanations

dialogue tags

The neuron detects dialogue attribution markers—verbs like “said,” “hissed,” or “growled,” speaker names, and the surrounding quotation punctuation.

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

-1.73

to

-1.66

are

-1.57

the

-1.53

 however

-1.51

 they

-1.39

 were

-1.38

 currently

-1.33

 thus

-1.33

 However

-1.30

POSITIVE LOGITS

這裡

1.41

 разные

1.41

 мы

1.40

FUENTES

1.38

 şeyi

1.38

あなたの

1.35

Зно

1.35

 cápsulas

1.35

هو

1.30

 моя

1.30

Activations Density 0.008%