INDEX

Explanations

G followed by numbers

The neuron selectively activates on instances of the standalone numeral “2” (e.g. in “G2 phase,” “2 VDC,” etc.).

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

you

-2.89

that

-2.64

 bahwa

-2.58

 That

-2.58

rowable

-2.33

ﮕ

-2.27

 ehemal

-2.20

готовление

-2.17

意味着

-2.11

)");

-2.11

POSITIVE LOGITS

of

2.36

 और

2.22

AdvEx

2.09

 memutus

1.98

ୈ

1.95

瘩

1.95

𓇼

1.95

。「

1.91

 και

1.91

biór

1.90

Activations Density 0.039%