INDEX

Explanations

originating or concerning specific entities

only retain footage

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

و

0.85

ون

0.66

ор

0.62

وون

0.61

ات

0.59

اد

0.59

ен

0.58

وا

0.56

ين

0.55

он

0.53

POSITIVE LOGITS

 {}>,

0.49

 irritated

0.48

 forth

0.47

 Acción

0.47

vif

0.47

Jf

0.46

 upstate

0.46

 impracticable

0.45

 Alpine

0.45

 inhib

0.45

Activations Density 0.000%