INDEX

Explanations

subject matter discussed or disclosed

The neuron specifically detects occurrences of the phrase “subject matter.”

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

</b>

-1.55

-1.52

It

-1.49

ி

-1.47

ка

-1.39

 ще

-1.38

 beter

-1.38

dengan

-1.36

指挥

-1.35

Whom

-1.35

POSITIVE LOGITS

 imó

1.73

 corresponding

1.72

 próprias

1.70

“

1.69

 Bedürf

1.66

of

1.65

 extremely

1.63

1.59

but

1.58

 escolas

1.57

Activations Density 0.003%