INDEX

Explanations

try to verbs

The neuron strongly activates on very common short English verbs (e.g. “get,” “do,” “use,” “keep,” “be,” 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

-1.69

 proposées

-1.64

Τ

-1.57

ziell

-1.55

IER

-1.55

༒

-1.52

Μ

-1.52

IMT

-1.52

Ꮂ

-1.49

 fournies

-1.47

POSITIVE LOGITS

an

1.41

 ones

1.40

迓

1.30

 допомо

1.30

遄

1.28

 legislación

1.27

GINIA

1.26

↵↵

1.24

 slight

1.20

 also

1.19

Activations Density 0.053%