INDEX

Explanations

excavation and excitation

The neuron detects occurrences of “excavate” and its morphological variants (e.g. excavation, excavating, excavators).

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

齶

-2.48

quelize

-2.38

}$

-2.30

腘

-2.23

のおすすめ

-2.23

 interessa

-2.20

ኅ

-2.19

 допомогти

-2.17

re

-2.17

 viewWillAppear

-2.14

POSITIVE LOGITS

↵

3.03

but

2.58

2.25

‘

2.22

 acostumb

2.17

浑身

2.13

 sheer

2.13

 останови

2.11

2.09

 decoradas

2.06

Activations Density 0.002%