INDEX

Explanations

authentication tokens and code comments

The neuron activates on code tokens related to authentication API calls (e.g. auth, signIn, createUserWithEmailAndPassword, user, password).

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

its

-1.67

 each

-1.34

-1.28

 these

-1.26

for

-1.23

\_

-1.21

 such

-1.20

-1.16

需要

-1.14

The

-1.11

POSITIVE LOGITS

Latvia

1.41

 ผู้หญิง

1.41

ਜ਼

1.34

Daha

1.31

Parque

1.31

Моя

1.29

 використовувати

1.27

Aç

1.23

𓂂

1.21

 rám

1.20

Activations Density 0.002%