INDEX

Explanations

solitary, solitude, solitaire

The neuron strongly activates on words derived from “solit–” (e.g. solitary, solitaire, solitude), i.e. terms denoting being alone or single.

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

 Púb

-2.70

aliśmy

-2.42

 biß

-2.33

 they

-2.30

 komplette

-2.27

to

-2.22

 остальные

-2.22

羮

-2.19

の部分

-2.16

 schönes

-2.16

POSITIVE LOGITS

许久

3.09

2.78

and

2.75

这也是

2.52

⪧

2.47

ttino

2.44

ный

2.41

)$,

2.25

this

2.25

ୌ

2.23

Activations Density 0.004%