INDEX

Explanations

questions involving pronouns

This neuron detects personal, subjective language — sentences that use first- or second-person perspective (I/you) describing experiences or directly addressing the reader.

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

あなたの

0.65

您的

0.61

 ваше

0.60

你的

0.57

 Ihrem

0.57

 আপনার

0.56

 вашу

0.55

 вашего

0.55

 ваша

0.54

 ваши

0.53

POSITIVE LOGITS

he

0.41

she

0.36

я

0.35

 он

0.34

 they

0.34

 mình

0.31

you

0.29

वह

0.28

we

0.27

0.26

Activations Density 0.130%