INDEX

Explanations

mentions of intrinsic properties or intrinsic characteristics

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

extAlignment

-0.77

seamnă

-0.71

OURI

-0.71

 StatefulWidget

-0.70

 Reſ

-0.69

 pinulongan

-0.69

Hochspringen

-0.68

 bezeichneter

-0.67

 rootReducer

-0.67

ScreenState

-0.65

POSITIVE LOGITS

 intrinsic

3.13

intrinsic

2.89

 Intrinsic

2.78

Intrinsic

2.61

 intrinsically

2.14

 intrins

1.97

insic

1.85

 extrinsic

1.60

 inherent

1.55

inher

1.29

Activations Density 0.012%