INDEX

Explanations

beginnings of phrases

The neuron activates on any numeric token—integers or decimals—i.e. it detects numbers or measurements in the 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

 when

-1.41

 while

-1.38

 time

-1.30

 with

-1.28

 both

-1.23

isNotNull

-1.23

 regardant

-1.23

ítez

-1.22

 lorsqu

-1.22

if

-1.20

POSITIVE LOGITS

 tacón

1.57

或是

1.55

 или

1.52

谖

1.49

或者

1.47

 우리

1.47

groet

1.46

 gebruiken

1.43

rester

1.40

GillaGilla

1.39

Activations Density 0.050%