INDEX

Explanations

references to person-specific pronouns and related words

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

িনি

-0.73

 Browne

-0.72

 Dubuque

-0.70

 Badger

-0.69

rž

-0.68

rophobic

-0.68

 CURIAM

-0.67

betic

-0.66

sns

-0.66

 RIPRODUZIONE

-0.66

POSITIVE LOGITS

it

2.77

It

2.30

It

2.17

它

2.05

它

1.84

its

1.80

 оно

1.68

Its

1.66

Its

1.63

nó

1.58

Activations Density 4.376%