INDEX

Explanations

citations and references

This neuron detects inline reference or footnote markers—that is, bracketed or superscripted citation numbers (e.g. “[1]”, “[ ^1]”, “[*1]”).

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

])->

-1.57

maxY

-1.45

THEN

-1.39

🥉

-1.39

//{

-1.37

}],

-1.32

 คา

-1.31

ulador

-1.31

 pourquoi

-1.30

requestCode

-1.29

POSITIVE LOGITS

 there

1.90

 sometimes

1.63

 when

1.60

 methods

1.57

 risposte

1.56

 gempa

1.55

 never

1.47

 seldom

1.45

 rarely

1.45

 currently

1.45

Activations Density 0.001%