INDEX

Explanations

hearing and listening

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

 между

-1.42

 часто

-1.33

 однако

-1.31

Even

-1.29

 даже

-1.28

-1.27

mockito

-1.23

mism

-1.22

 сада

-1.21

tahui

-1.20

POSITIVE LOGITS

commented

1.46

placed

1.32



1.31

 nový

1.30

ఝ

1.28

ى

1.27

 armazen

1.24

 увидел

1.23

 them

1.22

 MICHAEL

1.21

Activations Density 0.026%