INDEX

Explanations

measuring sensitivity and transmission

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

bestos

-1.45

cribes

-1.42

 ciebie

-1.41

惴

-1.35

 aprendizagem

-1.33

来到了

-1.31

]='

-1.31

cribing

-1.30

 glück

-1.29

跑到

-1.28

POSITIVE LOGITS

as

1.59

or

1.47

 when

1.39

Эти

1.31

and

1.26

ansvar

1.24

 dulu

1.23

tetés

1.22

 also

1.21

 while

1.20

Activations Density 0.355%