INDEX

Explanations

possessive pronouns followed by nouns

The neuron detects English possessive pronouns (e.g., my, his, her, its, their).

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

 otros

-1.66

 anderen

-1.63

or

-1.59

其他

-1.58

 svou

-1.50

หรือ

-1.47

 lainnya

-1.38

 остальные

-1.38

 يأ

-1.37

?"

-1.35

POSITIVE LOGITS

1.72

1.28



1.23

勦

1.16

馬上

1.14

引用元

1.13

谖

1.13

denn

1.12

 tentar

1.12

聼

1.11

Activations Density 0.129%