INDEX

Explanations

only followed by constraint

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

吒

2.84

ic

2.70

ש

2.67

ый

2.44

роме

2.39

 डायरेक्ट

2.36

“)

2.35

.”)

2.31

蓟

2.31

्रल

2.27

POSITIVE LOGITS

tter

2.55

யூ

2.36

தலாக

2.30

ivalence

2.24

ponin

2.23

هي

2.20

ifications

2.16

ह्म

2.13

konom

2.11

Ask

2.08

Activations Density 0.582%