INDEX

Explanations

take it or leave it

The neuron activates on occurrences of the verb “take” (and its inflected forms like “taking”) in a sentence.

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

錚

-1.35

 Reſ

-1.34

瞜

-1.31

excellents

-1.31

יקה

-1.29

 entonces

-1.29

一趟

-1.27

cht

-1.27

 atleast

-1.26

 decât

-1.26

POSITIVE LOGITS

1.37

</h3>

1.30

rophoresis

1.27

remadura

1.23

<sup>

1.21

เขา

1.20

";

1.20

 loro

1.16

$,

1.16

():

1.16

Activations Density 0.011%