INDEX

Explanations

activities and equipment

The neuron fires on any mention of “skate”/“skating” (including “Park,” “Skate,” “Skaters,” “street skating,” or the letters S-K-A-T-E).

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

↵↵↵↵

-1.34

-1.32

-1.30

↵↵↵↵↵

-1.27

↵↵

-1.27

is

-1.26

be

-1.25

-1.23

-1.22

POSITIVE LOGITS

)’

1.58

ahnya

1.57

droj

1.43

 monast

1.38

 그는

1.38

owohl

1.36

PreInfinity

1.34

AZIONI

1.33

otry

1.33

endorong

1.30

Activations Density 0.032%