INDEX

Explanations

references to diving or diving activities

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

 divergence

-1.34

diver

-1.23

 diver

-1.23

 Diver

-1.22

Diver

-1.19

 divergent

-1.16

 diverge

-1.10

 divert

-0.95

 diverging

-0.92

 diverted

-0.88

POSITIVE LOGITS

 dive

2.80

 diving

2.36

 dives

2.31

dive

2.23

 dived

2.20

 Dive

2.16

diving

2.08

Dive

1.98

 Diving

1.96

Diving

1.90

Activations Density 0.001%