INDEX

Explanations

asking to tailor further

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

<em>

1.01

<strong>

0.94

ตน

0.90

<sup>

0.86

 эта

0.82

брав

0.81

วาง

0.80

веро

0.79

 данным

0.77

ос

0.77

POSITIVE LOGITS

 jolie

1.73

 atthakath

1.71

ɹ

1.67

 kakak

1.66

。...

1.64

besiege

1.63

 hippie

1.63

 bouncy

1.60

়া

1.60

 celebs

1.60

Activations Density 0.502%