INDEX

Explanations

more [adjective/adverb]

This neuron is sensitive to comparative constructions introduced by “more.”

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

есть

0.82

েও

0.79

ARE

0.77

자가

0.76

 совета

0.74

sa

0.72

0.69

AH

0.68

cares

0.67

th

0.67

POSITIVE LOGITS

 than

1.21

 niż

1.19

än

1.16

 allá

0.95

 decât

0.93

 Than

0.93

 więcej

0.91

กว่า

0.88

 περισσότε

0.85

 ніж

0.84

Activations Density 0.000%