INDEX

Explanations

starting of phrases

This neuron detects numeric tokens, especially multi‐digit numbers such as dates and counts.

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

 Bete

-0.73

!\!\

-0.72

lenme

-0.72

áska

-0.71

厦

-0.69

がある

-0.67

 nadat

-0.66

theria

-0.65

 Mercer

-0.63

 escritor

-0.62

POSITIVE LOGITS

 Mathieu

0.84

bustion

0.83

 oficina

0.78

nok

0.78

サミ

0.75

ibatkan

0.74

Jor

0.74

FontOfSize

0.74

rines

0.74

 countryside

0.73

Activations Density 0.020%