INDEX

Explanations

even if / though / when

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

 than

-1.84

 également

-1.70

 igualmente

-1.63

 також

-1.62

 επίσης

-1.61

 also

-1.59

또

-1.59

 также

-1.58

 need

-1.55

 גם

-1.55

POSITIVE LOGITS

 when

2.23

 though

2.13

for

2.13

 because

2.00

 where

1.90

╣

1.69

our

1.68

 právě

1.64

سون

1.63

 those

1.63

Activations Density 0.009%