INDEX

Explanations

nested for loops

The neuron strongly fires on loop‐header tokens—especially the “for (” syntax and the loop variable/type declarations—i.e. it identifies for‐loops.

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

Alamat

-1.30

ſi

-1.28

 APPELL

-1.27



-1.24

 parachoque

-1.23

 rése

-1.22

 calendriers

-1.19

 favoris

-1.16

 klim

-1.16

 transparentes

-1.15

POSITIVE LOGITS

No

1.30

1.28

Due

1.25

1.23

1.21

In

1.20

…

1.20

 also

1.17

1.16

Activations Density 0.002%