INDEX

Explanations

left with bracket delimiters

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

 醤油

-1.91

戗

-1.90

-1.85

ꪔ

-1.81

 häufigsten

-1.81

Таблица

-1.77

-1.76

le

-1.74

 المهم

-1.73

OCOLATE

-1.70

POSITIVE LOGITS

 portero

2.23

：

2.19

.,"

2.16

.--

2.11

).

2.11

。

2.06

蓠

2.05

...."

2.03

when

1.99

Activations Density 0.001%