INDEX

Explanations

g

The neuron detects occurrences of the “e.g.” (for example) abbreviation.

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

in

-1.61

and

-1.60

 which

-1.36

or

-1.21

</h1>

-1.18

)=>{

-1.16

\}$,

-1.15

歓迎

-1.12

on

-1.11

by

-1.10

POSITIVE LOGITS

2.13

 verrou

1.42

 éta

1.40

 rafra

1.39

 rafraî

1.35

 refroid

1.34

 cinquante

1.30

 précip

1.30

 étan

1.28

 ceux

1.27

Activations Density 0.029%