INDEX

Explanations

numbers following '2'

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

ণ্ঠে

1.79

pport

1.75

چر

1.74

 ograni

1.72

!/"

1.71

tał

1.69

inz

1.69

চ

1.69

EXC

1.67

ሳት

1.63

POSITIVE LOGITS

वीं

2.56

esse

2.52

nın

2.50

 वीं

2.41

hams

2.27

obarb

2.24

hwar

2.11

mnt

2.08

ongrass

2.07

 మంది

2.05

Activations Density 0.746%