INDEX

Explanations

names and descriptive terms

The neuron activates on numeric tokens—i.e. any sequence of digits (including decimals) in the text.

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

-1.98

tht

-1.86

تنا

-1.84

 हालांकि

-1.84

 coupé

-1.75

ığımız

-1.73

цыі

-1.70

المل

-1.67

čno

-1.67

鸵

-1.66

POSITIVE LOGITS

2.64

’

2.56

2.34

2.09

川の

2.05

 amazingly

1.95

 kinda

1.92

re

1.89

,,

1.87

 doesn

1.83

Activations Density 0.005%