INDEX

Explanations

html input types

The neuron activates on HTML “input” tags (i.e. the `<input>` element and its `type` attribute values).

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

-1.74

与此同时

-1.50

but

-1.20

 tecnologie

-1.20

还不错

-1.20

があり

-1.16

はある

-1.15

だが

-1.13

はなく

-1.13

と

-1.12

POSITIVE LOGITS

gląda

1.37

 They

1.26

様な

1.22

ようです

1.20

ところに

1.13

のでしょう

1.10

為に

1.09

 belangrij

1.07

 japonaise

1.07

They

1.05

Activations Density 0.004%