INDEX

Explanations

This neuron activates on import statements in code.

import statements

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

猹

-1.32

uação

-1.32

𓐍

-1.30

最后由

-1.30

-1.28

oluble

-1.27

同时也

-1.27

 familien

-1.27

等到

-1.27

ENTINA

-1.27

POSITIVE LOGITS

 such

1.57

 アート

1.34

 краї

1.28

 світу

1.25

not

1.25

 notamment

1.22

ましょう

1.21

 nosi

1.21

1.17

Activations Density 0.010%