INDEX

Explanations

damn, darn, heck, freaking

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

 with

-1.81

ቍ

-1.66

Neden

-1.59

Bety

-1.58

趼

-1.55

 almofada

-1.54

賅

-1.54

崑

-1.53

皤

-1.50

 espere

-1.48

POSITIVE LOGITS

関する

1.88

<blockquote>

1.75

と言って

1.61

ꔹ

1.55

 tiefe

1.55

now

1.54

說道

1.52

 другая

1.48

ization

1.46

mica

1.46

Activations Density 0.007%