INDEX

Explanations

one of

This neuron detects demonstrative or enumerative referential phrases—especially “this one” and similar constructions that point to a specific item or instance.

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

 then

-1.53

기도

-1.27

Кому

-1.23

先は

-1.20

出去

-1.20

lück

-1.19

Ведущий

-1.18

 WaitForSeconds

-1.16

 rồi

-1.15

原始内容存档

-1.14

POSITIVE LOGITS

 that

2.42

 todėl

1.43

 dlatego

1.35

 these

1.34

 omdat

1.34

 mūsų

1.27

 those

1.27

 поэтому

1.22

pēc

1.22

 miest

1.21

Activations Density 0.157%