INDEX

Explanations

positioning ourselves or others

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

readlines

2.66

枒

2.61

read

2.60

নি

2.58

sts

2.57

sen

2.52

িকাংশ

2.46

reo

2.41

$>

2.39

speople

2.36

POSITIVE LOGITS

isasi

2.75

ي

2.68

ر

2.41

າງ

2.33

디오

2.22

megen

2.19

بے

2.18

ี

2.14

ാം

2.14

↵↵↵

2.12

Activations Density 0.002%