INDEX

Explanations

actions leading to exposure

physical manipulations or hand movements, particularly actions related to lifting, grabbing, or manipulating objects.

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

 that

-2.28

 this

-2.05

you

-1.86

 these

-1.55

or

-1.42

 because

-1.38

 when

-1.36

 here

-1.35

 бампер

-1.32

we

-1.31

POSITIVE LOGITS

 belli

1.41

 seksi

1.27

 oran

1.27

 saha

1.25

 favorita

1.23

וקה

1.20

 distante

1.20

ᐯ

1.20

 mercen

1.20

 några

1.20

Activations Density 0.012%