INDEX

Explanations

introducing scientific findings

The neuron detects the phrase "Here we show that" or similar phrases indicating presentation of research findings in scientific papers.

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

 then

-1.78

 either

-1.65

 each

-1.48

 themselves

-1.45

 others

-1.43

せば

-1.43

 needing

-1.41

for

-1.41

 both

-1.40

 entweder

-1.39

POSITIVE LOGITS

1.50

}=\

1.45

ᐅ

1.40

getCause

1.35

 projets

1.35

 poches

1.34

Ⅳ

1.32

+=(

1.30

 такой

1.30

 沖縄

1.30

Activations Density 0.384%