INDEX

Explanations

inappropriate behavior or activity

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

嵛

-2.58

rightarrow

-2.05

巂

-2.03

 είναι

-1.98

℟

-1.98

}$

-1.95

 metų

-1.94

 lancia

-1.92

ÁCT

-1.92

to

-1.91

POSITIVE LOGITS

↵

2.63

辚

2.03

 techniczne

1.96

というか

1.95

gées

1.90

⡪

1.88

⢓

1.80

幾天

1.80

ifies

1.79

をはじめ

1.77

Activations Density 0.004%