INDEX

Explanations

curiosity and buoyancy

The neuron detects occurrences of the word “curiosity” (and its close variants) in the text.

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

ar

-2.97

With

-2.91

When

-2.84

！"

-2.63

 menyen

-2.63

Without

-2.42

♡♡

-2.42

る

-2.41

方法

-2.39

基础

-2.36

POSITIVE LOGITS

3.50



2.69

</h4>

2.61

 andererseits

2.50

ༀ

2.45

趼

2.41

蟑

2.41

没办法

2.36

蛱

2.33

 ferv

2.30

Activations Density 0.002%