INDEX

Explanations

function calls

The neuron fires on function or method names at the point where they’re being invoked (i.e. identifiers immediately followed by an opening parenthesis).

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

‘

-1.16

 acht

-1.09

 デニム

-1.08

 ニット

-1.07

arsi

-1.05

THAT

-1.01

 lokale

-0.99

the

-0.96

 astounding

-0.96

/***

-0.96

POSITIVE LOGITS

 with

1.72

 without

1.57

by

1.43

 even

1.41

 только

1.30

 даже

1.29

 only

1.28

 from

1.27

 навіть

1.25

 тільки

1.20

Activations Density 0.005%