INDEX

Explanations

describes a state or property

The neuron strongly fires on copular linking verbs (e.g. “is,” “are,” “It is,” “They are”) that introduce definitional or descriptive statements.

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

 будут

-1.35

 بودند

-1.27

ētu

-1.16

ходили

-1.13

 خواهند

-1.09

álna

-1.09

 میکنم

-1.09

 میکنه

-1.09

ར

-1.07

 fichero

-1.02

POSITIVE LOGITS

is

3.20

was

2.41

can

2.27

has

2.11

 been

1.47

 gained

1.43

are

1.41

还可以

1.38

 also

1.30

也可以

1.25

Activations Density 0.358%