INDEX

Explanations

various states and actions

The neuron primarily responds to plural noun forms—words ending in “s” that denote groups, events, or collections.

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

in

-1.53

use

-1.21

始めた

-1.19

 during

-1.13

 before

-1.10

 approach

-1.06

 even

-1.05

 view

-1.04

 некоторых

-1.03

บาง

-1.02

POSITIVE LOGITS

 entweder

1.64

各种

1.43

 either

1.38

要么

1.28

 olika

1.22

Either

1.21

 különböző

1.19

 parachoque

1.18

 berbagai

1.16

 everywhere

1.15

Activations Density 0.108%