INDEX

Explanations

variables indexed by $i$ or $n$

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

for

-1.97

 while

-1.95

 what

-1.93

as

-1.90

</td>

-1.88

</h2>

-1.87

</h6>

-1.80

to

-1.70

 well

-1.69

 With

-1.69

POSITIVE LOGITS

 incredi

1.76

oon

1.72

 arriver

1.69

 anhänger

1.63

 expli

1.60

 ofte

1.59

 dien

1.58

ſu

1.57

 ocas

1.54

famous

1.53

Activations Density 0.020%