INDEX

Explanations

descriptive adjectives

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

 this

-2.77

 when

-2.20

 because

-2.11

 where

-1.83

for

-1.80

in

-1.80

This

-1.63

снимок

-1.55

обзор

-1.49

 diesen

-1.45

POSITIVE LOGITS

 same

1.59

same

1.50

worpen

1.41

 همان

1.39

 electricidad

1.38

 ранее

1.34

 одной

1.33

 hábit

1.30

므

1.30

 wana

1.28

Activations Density 0.142%