INDEX

Explanations

negative numbers and subtraction

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

ུ་

-1.00

*=

-0.92

 Multiply

-0.82

 multiply

-0.78

峇

-0.76

 hilsen

-0.75

Multiply

-0.74

wisata

-0.73

multiply

-0.73

 چشم

-0.72

POSITIVE LOGITS

 negative

1.65

 minus

1.45

negative

1.38

Negative

1.37

minus

1.23

Minus

1.17

 Negative

1.12

 negativo

1.05

 subtraction

1.05

 negativos

1.05

Activations Density 0.045%