INDEX

Explanations

specific compound terms

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

怄

-1.35

 brooks

-1.28

ということです

-1.25

-1.23

 اون

-1.23

 rile

-1.22

 infancia

-1.20

 pratiquer

-1.20

 condol

-1.20

钣

-1.20

POSITIVE LOGITS

and

1.91

子は

1.55

AND

1.49

 Προ

1.48

！（

1.45

၇

1.43

 senaste

1.41

 JUST

1.41

子が

1.40

 oraz

1.37

Activations Density 0.201%