INDEX

Explanations

words used to describe physical or mental suffering

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

exitRule

-0.63

antaranya

-0.63

 bahawa

-0.61

<bos>

-0.57

 lesquelles

-0.57

 kterou

-0.56

 laquelle

-0.55

 impossível

-0.53

 fatti

-0.53

 lequel

-0.53

POSITIVE LOGITS

0.68

 meaning

0.63

DeleteBehavior

0.57

GEBURTSDATUM

0.56

 Meaning

0.56

胱

0.50

‐

0.50

Meaning

0.49

-{

0.48

expandindo

0.47

Activations Density 31.284%