INDEX

Explanations

code comments, assertions

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

фр

-0.93

<0xD7>

-0.90

 previos

-0.87

𝒐

-0.86

of

-0.85

ṱ

-0.85

ᶰ

-0.85

號

-0.84

="{{

-0.84

र्म

-0.84

POSITIVE LOGITS

↵

0.81

<eos>

0.80

 emosi

0.77

重い

0.77

 zwei

0.77

かつ

0.76

CIUDAD

0.76

innig

0.75

 две

0.75

Activations Density 0.080%