INDEX

Explanations

shape and size

The neuron fires strongly on physical‐attribute terms—especially the word “shape” (and similar dimensional descriptors).

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

 $^{\

-1.84

neling

-1.71

vení

-1.58

鱿

-1.56

を表示

-1.55

がこの

-1.55

ことです

-1.53

}^{\

-1.52

Not

-1.52

POSITIVE LOGITS

 shapes

1.91

 shape

1.84

 minimalista

1.78

klere

1.77

หรือ

1.72

 djur

1.70

 öns

1.68

 pessoas

1.67

 fön

1.66

躄

1.66

Activations Density 0.059%