INDEX

Explanations

at the end

The neuron strongly activates on four-digit numeric tokens (e.g. years or other four-digit numbers).

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

τυχ

-0.94

inę

-0.93

 marbre

-0.89

initial

-0.88

いに

-0.85

Initial

-0.84

 désol

-0.84

宬

-0.83

starts

-0.82

ígen

-0.82

POSITIVE LOGITS

end

6.13

end

2.80

 конце

2.73

 ends

2.67

 ending

2.63

End

2.44

 ended

2.41

End

2.36

END

2.33

 conclusion

2.28

Activations Density 0.042%