INDEX

Explanations

said followed by name or he/she

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

 THEY

-1.01

crocs

-0.99

 THESE

-0.96

satin

-0.92

 этих

-0.92

 なく

-0.90

tafogo

-0.90

maillot

-0.89

 gemeinsame

-0.89

≦)

-0.88

POSITIVE LOGITS

۱۹

1.04

niere

1.01

أم

1.01

dö

0.98

lös

0.97

ğlık

0.97

 ケーブル

0.97

无论是

0.96

下来的

0.96

 alcun

0.95

Activations Density 0.289%