INDEX

Explanations

yourself or others

This neuron activates on second-person imperative/reflexive phrases using “yourself,” such as “make yourself at home,” “give yourself applause,” or “allow yourself to be seen.”

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

自己

1.28

 themselves

1.27

自分が

1.24

自己在

1.23

 himself

1.23

 dirinya

1.21

 себе

1.20

自分の

1.19

 نفسها

1.16

 itself

1.16

POSITIVE LOGITS

ständig

0.78

доста

0.75

豪

0.72

к

0.70

ändig

0.69

ಗಾರ

0.67

ে

0.66

と言う

0.65

osyl

0.65

 anew

0.65

Activations Density 0.109%