INDEX

Explanations

comment lines

The neuron fires on standalone numeric tokens (e.g. line numbers or similar numeric literals).

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

-1.41

of

-1.34

on

-1.22

 both

-1.20

 Kommune

-1.17

werf

-1.16

کتری

-1.06

 reise

-1.05

 Etik

-1.05

 breed

-1.05

POSITIVE LOGITS

どうやって

1.38

 accesorio

1.22

 mejoras

1.20

今度

1.20

 brimming

1.16

ཾ

1.16

 sebagainya

1.16

雰囲

1.15

 verdaderos

1.15

认真的

1.13

Activations Density 0.007%