INDEX

Explanations

cute or charming descriptions

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

-1.66

ar

-1.49

洐

-1.40

 przód

-1.35

如何

-1.34

 directly

-1.31

os

-1.30

ть

-1.30

}:

-1.30

ta

-1.28

POSITIVE LOGITS

 kleine

1.56

kleine

1.53

⼩

1.41

 малень

1.39

 cinnamon

1.38

 naïve

1.37

 أنها

1.36

 disdain

1.32

 små

1.31

 flirt

1.31

Activations Density 0.025%