INDEX

Explanations

specific phrases and names

The neuron strongly activates on descriptions of curriculum or course learning objectives — e.g. statements of what students will read, know, or be able to do.

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

we

-1.33

 venía

-1.27

 absolutely

-1.27

 really

-1.25

nemone

-1.24

voici

-1.19

izamos

-1.16

 here

-1.14

so

-1.12

に於

-1.12

POSITIVE LOGITS

ilions

1.23

 myös

1.20

也能

1.19

 bytu

1.19

 distinctive

1.16

āja

1.16

ällor

1.13

ją

1.12

懌

1.11

 festgelegt

1.10

Activations Density 0.021%