INDEX

Explanations

The neuron strongly activates on specialized scientific and technical terms (e.g. “functions,” “organelles,” “metabolism,” “techniques,” “treatments”) characteristic of formal, academic writing.

introducing example lists

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

and

-1.45

 only

-1.31

 pidió

-1.30

endaftaran

-1.29

 horribly

-1.27

 aptly

-1.26

 actually

-1.23

 declaró

-1.22

 took

-1.21

 Actually

-1.21

POSITIVE LOGITS

 such

6.31

 like

3.53

such

3.52

 including

3.41

 таких

3.38

 такие

3.36

 telles

2.95

比如

2.78

Such

2.77

 takich

2.70

Activations Density 0.370%