INDEX

Explanations

forms of the verb "listen".

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

aarrggbb

-0.78

udesta

-0.75

 craindre

-0.75

 Sprague

-0.73

 piú

-0.73

 cref

-0.71

Референце

-0.70

ContentAlignment

-0.69

 quelcon

-0.68

 nuages

-0.67

POSITIVE LOGITS

 listen

1.09

 listening

1.06

 listened

1.01

 Listening

1.00

 listens

0.98

 Listen

0.94

 LISTEN

0.91

 listeners

0.89

Listen

0.86

Listening

0.85

Activations Density 0.006%