INDEX

Explanations

two or more

The neuron spikes on the word “two” (often in the phrase “two … at the same time”), i.e. it detects mentions of two concurrent items or operations.

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

hā

-1.26

 doda

-1.11

 zara

-1.11

бр

-1.10

JM

-1.06

 también

-1.06

Ṛ

-1.05

 zako

-1.05

marginBottom

-1.05

";

-1.05

POSITIVE LOGITS

 including

1.20

 사업

1.16

ULING

1.16

 législation

1.16

 blijft

1.13

中略

1.13

 this

1.13

「

1.11

Điều

1.11

⯈

1.10

Activations Density 0.167%