INDEX

Explanations

domain specific nouns

This neuron detects English technical or domain-specific noun tokens (e.g. “field,” “service,” “column,” “question,” etc.).

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

and

-1.17

了许多

-1.09

 quelli

-1.04

性和

-0.95

 ↓,

-0.91

Ingrédients

-0.90

 mostly

-0.90

Quali

-0.89

了很多

-0.89

 profonda

-0.89

POSITIVE LOGITS

 that

1.62

of

1.46

 given

1.41

 tersebut

1.18

ที่

1.16

 chosen

1.13

 monasterio

1.10

tersebut

1.04

ındaki

1.04

 selected

1.02

Activations Density 0.114%