INDEX

Explanations

indicating established facts

The neuron flags occurrences of the word “known” (especially in phrases like “is known to” or “it is well known that”).

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

୩

-1.77

ۜ

-1.48

-------

-1.41

rame

-1.38

 eher

-1.35

 whom

-1.33

および

-1.33

abancı

-1.31

</h2>

-1.27

phäre

-1.27

POSITIVE LOGITS

、【

1.66

 sabido

1.52

 інших

1.43

 memungkinkan

1.38

 melibatkan

1.34

 According

1.33

 але

1.32

 diketahui

1.32

 лікар

1.32

 After

1.30

Activations Density 0.079%