INDEX

Explanations

No Explanations Found

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

聡

1.13

 metric

1.10

 ernst

1.08

 measurable

1.06

 труд

1.04

 humility

1.03

 uncertainty

1.02

measurable

1.02

 vision

1.01

𝘪

1.00

POSITIVE LOGITS

èng

1.32

ผ่น

1.28

یکیشن

1.27

uber

1.27

ogon

1.24

 добавля

1.24

副

1.21

asida

1.20

âteau

1.19

ód

1.17

Activations Density 0.008%

No Known Activations