INDEX

Explanations

"your" / "we" / "i'm"

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

(?)

1.88

(?)

1.79

-/

1.75

usually

1.58

1.55

(-)

1.54

 Apparently

1.49

 Usually

1.47

 miscellaneous

1.47

比較的

1.47

POSITIVE LOGITS

 bipartisan

1.83

 mūsų

1.81

 devons

1.74

Chúng

1.71

 profondément

1.70

 dobbiamo

1.69

 nossas

1.69

ımızın

1.67

 nostre

1.67

 nossa

1.65

Activations Density 0.727%