INDEX

Explanations

pronoun subject followed by verb

This neuron detects instances of reported speech or dialogue attribution—especially sentences that begin with a pronoun (He/She) introducing what someone says or does, often marked by a colon.

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

 them

-1.85

ła

-1.75

say

-1.74

那些

-1.73

mohon

-1.70

 той

-1.58

 slik

-1.56

och

-1.55

その

-1.52

льные

-1.52

POSITIVE LOGITS

を紹介

1.94

 poté

1.88

起码

1.75

 Anſ

1.72

 aseguró

1.71

㈱

1.70

ネットで

1.64

 vroeger

1.63

 ofrecemos

1.58

他们是

1.52

Activations Density 0.022%