INDEX

Explanations

actions followed by prepositions

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

 that

-1.55

 anunció

-1.35

mostly

-1.34

឵

-1.33

 áudio

-1.30

mainly

-1.27

primarily

-1.27

 revanche

-1.23

************

-1.22

ֱ

-1.21

POSITIVE LOGITS

 what

1.42

 from

1.31

by

1.29

of

1.27

 sabias

1.23

'].

1.23

so

1.21

nemers

1.20

 durch

1.19

as

1.15

Activations Density 0.153%