INDEX

Explanations

narrative elements and duration

The neuron fires on evaluative terms and measurements in critiques—especially negative judgments about pacing, length, or coherence (e.g. “tedious,” “boring,” “confusing,” “hours,” “minutes,” “flow”).

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

-1.33

by

-1.31

-1.29

-1.25

-1.24

-1.23

on

-1.22

-1.20

-1.18

 lorsqu

-1.13

POSITIVE LOGITS

 Mexique

1.34

ṝ

1.26

它的

1.25

 "'";

1.24

Setelah

1.23

chränk

1.21

 Mondiale

1.20

 insanların

1.20

 "}";

1.18

নের

1.18

Activations Density 0.052%