INDEX

Explanations

abroad, overseas, goods effects

The neuron is keyed to numeric tokens and values (digits, numbers, timestamps, and numeric expressions).

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

 Khmer

-1.04

ihn

-0.97

از

-0.85

 sovi

-0.84

ブリ

-0.80

rua

-0.79

 Sudanese

-0.79

mov

-0.79

 GUID

-0.79

 onun

-0.78

POSITIVE LOGITS

 ours

1.26

our

1.16

 atasan

1.12

 meille

1.05

 Americans

1.05

 western

1.05

 우리

1.03

Closer

1.01

américa

0.97

 Western

0.96

Activations Density 0.119%