INDEX

Explanations

instituts et laboratoires

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

 klasa

-0.71

倭

-0.70

 Switzerland

-0.69

OFFSET

-0.69

 planetary

-0.69

 Calm

-0.68

 reikia

-0.68

 World

-0.68

 quinn

-0.67

 Problem

-0.66

POSITIVE LOGITS

𝒥

0.90

دانشنامهٔ

0.85

 labelled

0.82

 թվ

0.81

 Kremlin

0.81

였

0.80

หลัง

0.80

՜

0.79

 laboratorio

0.79

getLabel

0.78

Activations Density 0.040%