INDEX

Explanations

dates and times

The neuron primarily detects numeric tokens (e.g. dates, years, percentages, or other 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

in

-1.48

 QtWidgets

-1.33

𓋼

-1.31

Their

-1.24

<0xF0>

-1.21

₧

-1.19

 Jér

-1.16

 msglen

-1.16

 baloncesto

-1.16

 QtGui

-1.15

POSITIVE LOGITS

ांकि

1.40

 obfusc

1.38

 cuando

1.34

 castig

1.32

 Когда

1.30

㌧

1.27

 devast

1.21

 quando

1.21

了许多

1.20

âce

1.17

Activations Density 0.047%