INDEX

Explanations

delay

This neuron detects references to time delays—e.g., the word “delay” (and variants) often accompanied by numeric parameters or macros.

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

?”

-2.83

’

-2.58

 albeit

-2.30

 fearful

-2.16

 enduring

-2.16

”?

-2.11

」

-2.09

.”

-2.08

and

-2.06

POSITIVE LOGITS

ﮩ

2.31

珰

1.96

 plupart

1.93

интере

1.90

ruguay

1.90

ଝ

1.88

我们

1.85

так

1.82

geſ

1.81

it

1.79

Activations Density 0.005%