INDEX

Explanations

results

The neuron fires on occurrences of the word “result” or “results.”

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

to

-1.59

ID

-1.55

 awakeFromNib

-1.54

}}$

-1.48

kében

-1.48

},

-1.48

();

-1.41

"});

-1.41

for

-1.35

POSITIVE LOGITS

 tunik

1.51

点此

1.47

ודים

1.45

 pôr

1.38

 capucha

1.36

 anoche

1.35

︱

1.34

 comiendo

1.32

 soportar

1.29

 postales

1.29

Activations Density 0.099%