INDEX

Explanations

first name followed by last name

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

 himself

-1.15

这些

-1.05

 onları

-1.03

himself

-1.02

 discul

-0.99

inawa

-0.97

 poby

-0.96

nesc

-0.94

 sonrası

-0.94

 içi

-0.93

POSITIVE LOGITS

 herself

1.10

1.05

改为

1.02

 without

0.98

who

0.98

of

0.98

DeleteMapping

0.98

 stycznia

0.96

必须要

0.96

变更

0.95

Activations Density 0.003%