INDEX

Explanations

finding sources for details

The neuron flags words that introduce pointers to further information or references—terms like “details,” “more,” “information,” “definitions,” or “detailed” in “For … see” or “For … on” style phrases.

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

 anuncia

-1.40

 coment

-1.39

 compared

-1.35

 потому

-1.34

谢谢你

-1.32

mands

-1.30

itively

-1.30

alties

-1.28

 tyto

-1.27

POSITIVE LOGITS

$,

1.58

 which

1.54

}$,

1.48

)$,

1.48

(),

1.45

 please

1.44

 whose

1.39

”,

1.36

 yourself

1.34

 اینکه

1.30

Activations Density 0.057%