INDEX

Explanations

setter functions or method definitions

The neuron flags tokens that introduce or define a function/method (e.g. “void,” “function,” “set,” “def”)—i.e. it detects function or method declarations.

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

扨

-1.09

athed

-1.08

และ

-1.06

 hebben

-1.06

 mieli

-1.05

 struk

-1.05

麃

-1.04

 gebruiken

-1.03

 kontin

-1.03

 anunció

-1.02

POSITIVE LOGITS

 with

1.41

 while

1.23

 Even

1.16

for

1.12

 will

1.07

 even

1.04

 tiny

1.03

set

1.02

 While

1.02

 after

0.98

Activations Density 0.001%