INDEX

Explanations

technical questions

The neuron fires on code identifier tokens—names of functions, types, constructors, modules, or type variables in programming text.

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

for

-1.72

 düşük

-1.41

zei

-1.38

classed

-1.36

was

-1.35

}}{\

-1.34

 perles

-1.33

 косме

-1.32

holms

-1.30

 indien

-1.28

POSITIVE LOGITS

 grossa

1.70

無論

1.68

 znaleźć

1.66

 acogedor

1.60

 icona

1.55

 tunik

1.49

 there

1.48

㩒

1.47

 fået

1.46

 حسين

1.45

Activations Density 0.004%