INDEX

Explanations

Manhattan College

The neuron activates on numeric literals (integers or 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

^(@

-1.16

 unless

-1.13

淡淡的

-1.09

 maailman

-1.06

unless

-1.05

 コーデ

-1.05

וּ

-1.04

пыт

-1.03

 Suomessa

-1.02

şap

-1.01

POSITIVE LOGITS

 enable

1.13

());

1.10

Жизнь

1.09

گروه

1.08

 will

1.06

 allow

1.02

 enthusiastic

1.02

 buscado

1.01

 cintas

1.00

 sacar

0.99

Activations Density 0.000%