INDEX

Explanations

home and related contexts

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

د

3.27

2.78

دع

2.77

ات

2.66

2.61

ধানে

2.58

़

2.56

sla

2.54

ার্ভ

2.43

ा

2.41

POSITIVE LOGITS

<bos>

2.64

ন্ত্রণাল

2.35

 hiểm

2.33

coming

2.24

ગી

2.22

grabbing

2.22

~=

2.20

inate

2.20

AsUpIndicator

2.16

𝒌

2.16

Activations Density 0.254%