INDEX

Explanations

verbs indicating states or actions

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ORMAL

-1.38

 trei

-1.28

ığınız

-1.25

 فرزند

-1.23

Zurück

-1.23

᩠

-1.22

kset

-1.21

Deux

-1.20

 rodea

-1.20

 tornare

-1.20

POSITIVE LOGITS

its

1.63

 there

1.47

<sup>

1.27

 его

1.23



1.18

1.17

to

1.17

on

1.16

 jego

1.15

いため

1.13

Activations Density 0.292%