INDEX

Explanations

This neuron identifies code tokens corresponding to function or method calls (i.e. invocation names).

start activity, show dialog

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

其

-1.30

leyen

-1.28

\_\_

-1.27

ченных

-1.26

tı

-1.26

бера

-1.24

⚋

-1.24

 muualla

-1.24

 fhort

-1.23

themselves

-1.22

POSITIVE LOGITS

it

1.67

1.45

するので

1.30

たしか

1.25

1.23

 from

1.20

参考に

1.19

がたくさん

1.18

Activations Density 0.000%