INDEX

Explanations

common articles, prepositions, conjunctions

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

 vorder

-1.06

Mor

-0.97

↵

-0.97

 both

-0.95

 Amer

-0.94

 post

-0.93

is

-0.93

咐

-0.91

â

-0.90

-0.88

POSITIVE LOGITS

 škola

1.24

 divertente

1.15

burton

1.15

 pecados

1.12

couvrir

1.11

dő

1.06

Nazionale

1.06

鋨

1.05

來

1.03

raujo

1.03

Activations Density 0.099%