INDEX

Explanations

aimed at

This neuron detects words expressing direction toward or targeting something—especially the verb “aimed” and following preposition “at” indicating purpose.

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

 some

-2.19

 more

-2.16

Some

-1.81

two

-1.77

｢

-1.75

Even

-1.73

''

-1.72

 both

-1.69

 less

-1.68

With

-1.67

POSITIVE LOGITS

 ранее

1.87

 permitan

1.58

玙

1.47

镚

1.40

ufnahme

1.38

 instig

1.35

 maniere

1.35

is

1.34

蚨

1.33

mpion

1.31

Activations Density 0.066%