INDEX

Explanations

the word "also" and words that commonly follow it like "think", "start", "still", "notice", "include", "turn", or "by".

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

 Khat

-0.72

est

-0.69

ndham

-0.68

nin

-0.67

tic

-0.66

len

-0.65

nī

-0.65

óp

-0.64

lè

-0.63

OMET

-0.62

POSITIVE LOGITS

 also

1.63

also

1.54

 ALSO

1.53

 Also

1.43

Also

1.43

ALSO

1.41

 tambien

1.34

кож

1.32

 también

1.31

 Também

1.31

Activations Density 0.901%