INDEX

Explanations

find

The neuron strongly detects occurrences of the verb “find” (and its inflected form “finding”).

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

ᚔ

-1.41

Kapitel

-1.33

 נגד

-1.32

 家族

-1.23

ไป

-1.20

 errone

-1.20

硚

-1.18

 contextLoads

-1.18

訃

-1.17

مقال

-1.16

POSITIVE LOGITS

in

1.61

 such

1.41

 would

1.34

new

1.29

on

1.28

1.22

useNewUrlParser

1.20

 with

1.13

 Kró

1.13

any

1.12

Activations Density 0.084%