INDEX

Explanations

The neuron spikes on numeric expressions—particularly multi‐digit numbers, times, measurements, or version/decimal values.

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

函數

0.80

 characterize

0.80

↵

0.79

 emphasize

0.79

πο

0.78

看護

0.77

蔻

0.77

be

0.76

𝐪

0.75

angular

0.72

POSITIVE LOGITS

 propias

0.89

 bliss

0.88

"})

0.87

 vistas

0.86

 recorr

0.84

 vidas

0.83

 себя

0.81

 hesap

0.81

 знает

0.80

 hijas

0.80

Activations Density 0.000%