INDEX

Explanations

Singapore

The neuron activates on mentions of “Singapore” (and closely related proper nouns like Singaporean places, institutions, and titles).

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

 çanta

-1.35

鼕

-1.31

 kjer

-1.29

곳

-1.27

 bileklik

-1.24

 folosit

-1.23



-1.22

鏊

-1.22

 kolye

-1.21

 小物

-1.21

POSITIVE LOGITS

</td>

1.33

↵↵↵↵↵

1.20

1.17

↵↵↵↵↵↵

1.16

1.13

<sup>

1.13

то

1.12

↵↵↵

1.08

<strong>

1.08

Activations Density 0.061%