INDEX

Explanations

started programming or learning

The neuron is essentially a sentence‐boundary detector, spiking strongly on full stops (and the tokens that start or end sentences).

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

 there

-1.65

 then

-1.42

if

-1.37

 would

-1.32

 might

-1.28

There

-1.19

 should

-1.16

there

-1.16

需要

-1.13

you

-1.11

POSITIVE LOGITS

my

1.63

mainly

1.31

mostly

1.30

 principalement

1.28

//!

1.27

 combustível

1.25

 fechar

1.20

 reduzir

1.18

1.16

 ativar

1.16

Activations Density 0.149%