INDEX

Explanations

unwanted

The neuron activates on negative‐qualifier terms expressing something unwanted or undesired (e.g. “unwanted,” “undesired”).

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

 their

-1.57

-1.56

nachron

-1.35

gelöst

-1.33

 will

-1.31

-1.30

ặp

-1.26

for

-1.25

 tante

-1.22

on

-1.21

POSITIVE LOGITS

ญี่ป

1.77

の方法

1.66

 desay

1.64

 velikost

1.64

 unwelcome

1.52

 Diese

1.42

 dnes

1.41

 combinar

1.41

ครื่อง

1.40

 botellas

1.37

Activations Density 0.042%