INDEX

Explanations

signed or unsigned numbers

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

 negative

-0.86

NEGATIVE

-0.73

 negatives

-0.73

Negative

-0.72

negative

-0.70

 contenders

-0.67

ందు

-0.67

RECOMM

-0.67

quiera

-0.66

 négatif

-0.66

POSITIVE LOGITS

 zero

2.19

zero

1.80

 Zero

1.78

1.76

Zero

1.73

 ZERO

1.73

 neutral

1.63

(+

1.61

$+

1.60

ZERO

1.53

Activations Density 0.073%