INDEX

Explanations

underage crowd, commenting tools

The neuron fires on descriptive adjectives.

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

𓇼

-2.13

-2.05

-1.97

Not

-1.83

),

-1.81

 Even

-1.80

 Getting

-1.73

 regresó

-1.71

-1.66

but

-1.65

POSITIVE LOGITS

,’”

2.42

刖

2.33

 dueños

2.27

 rivales

2.11

,“

2.05

 voisins

2.05

 multe

2.03

缫

2.02

…」

2.00

܆

1.98

Activations Density 0.000%