INDEX

Explanations

words ending in 'ering'

The neuron strongly activates on words ending with the suffix “ering.”

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

-2.80

をしています

-2.63

會有

-2.55

風險

-2.36

轶

-2.30

 godziny

-2.22

中です

-2.19

或者

-2.17

 reason

-2.14

点的

-2.13

POSITIVE LOGITS

퐹

2.64

</h3>

2.63

ering

2.63

…)

2.59

鴣

2.52

罴

2.44

 includ

2.33

辔

2.31

 concomitant

2.30

也要

2.28

Activations Density 0.028%