INDEX

Explanations

the word "self"

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

RectangleBorder

-0.66

gonic

-0.62

 adiabatic

-0.59

hagic

-0.59

 يتيمه

-0.57

 epidem

-0.54

 Mohr

-0.54

okon

-0.53

akon

-0.53

POSITIVE LOGITS

 виправивши

0.73

HostException

0.67

 Gators

0.67

 carbu

0.66

 Loomis

0.66

ingtones

0.65

Eſ

0.64

estacks

0.64

 EClass

0.64

;*/

0.63

Activations Density 0.013%