INDEX

Explanations

it's or that's followed by verbs

The neuron responds to occurrences of the character “t” within tokens (including standalone “t” tokens and words containing “t”).

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

⚋

-1.48

 Another

-1.45

 Recently

-1.30

 поговори

-1.29

ired

-1.28

тс

-1.27

년

-1.27

-1.24

 bestehenden

-1.24

quelize

-1.24

POSITIVE LOGITS

at

1.77

 also

1.38

of

1.26

跡

1.23

 other

1.19

 residuos

1.18

 region

1.16

}';

1.16

wakilan

1.16

 ネット

1.13

Activations Density 0.019%