INDEX

Explanations

references to a character named Tom Ok

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

OK

-0.94

 AssemblyTitle

-0.88

 postIndex

-0.80

RegressionTest

-0.79

 okay

-0.79

 nakalista

-0.78

 <=",

-0.78

WithIOException

-0.77

 виправивши

-0.76

OSA

-0.75

POSITIVE LOGITS

ok

2.30

okkal

1.05

okk

1.01

okat

0.83

okin

0.75

okon

0.70

oks

0.68

oku

0.67

oka

0.60

okra

0.60

Activations Density 0.002%