INDEX

Explanations

fame and hall of fame

The neuron activates on occurrences of the word “fame.”

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

၉

-2.50

så

-2.39

梘

-2.36

相当于

-2.23

迓

-2.19

iocene

-2.16

 "'");

-2.16

 multitude

-2.16

闥

-2.14

是什么意思

-2.13

POSITIVE LOGITS

3.63

iſter

3.25

2.86

’

2.80

 harten

2.55

 bénévol

2.33

냑

2.33

 gemis

2.28

 Tenemos

2.27

 berdua

2.27

Activations Density 0.003%