INDEX

Explanations

turn to

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

 turn

-1.58

 turning

-1.32

Turn

-1.27

 Turn

-1.20

turn

-1.17

 TURN

-1.13

 turned

-1.13

 turns

-1.05

 turno

-1.05

TURN

-1.02

POSITIVE LOGITS

 resorted

1.15

 recourse

1.13

 resort

0.94

 again

0.93

 снова

0.93

 recurrir

0.88

again

0.83

resort

0.81

 vaak

0.80

to

0.79

Activations Density 0.019%