INDEX

Explanations

scientific and statistical descriptors

The neuron detects technical terms that describe research methods, study designs, or analytical procedures.

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

 hebben

-1.48

curated

-1.45

⬩

-1.40

龱

-1.34

stel

-1.31

ELTS

-1.30

zzet

-1.30

 воспита

-1.30

kimono

-1.27

 retracted

-1.27

POSITIVE LOGITS

by

2.19

1.91

as

1.52

 then

1.50

of

1.41

↵↵↵

1.33

 there

1.33

 November

1.23

to

1.23

 September

1.18

Activations Density 0.250%