INDEX

Explanations

commands and actions

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

 wszyscy

-1.16

 internetu

-1.13

ledad

-1.09

 garantir

-1.05

 akumulator

-1.05

 metodi

-1.04

 绘画

-1.03

 ftate

-1.03

zni

-1.02

 warszawa

-1.01

POSITIVE LOGITS

if

1.27

 immediately

1.13

or

1.09

 easy

0.97

by

0.97

 after

0.96

 detailed

0.91

as

0.90

on

0.90

do

0.90

Activations Density 0.002%