INDEX

Explanations

distinguishing from others

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

to

-1.91

 excellente

-1.62

𓍊

-1.61

橚

-1.52

出てくる

-1.47

ྃ

-1.42

話は

-1.42

 počet

-1.41

 температуре

-1.41

伝わ

-1.37

POSITIVE LOGITS

巾

1.74

䊐

1.68

。

1.63

 réglementation

1.54

ільки

1.53

 this

1.52

).

1.51

々木

1.50

$.

1.48

Activations Density 0.026%