INDEX

Explanations

file on video

The neuron strongly activates on long dash or em‐dash characters (extended punctuation marks) in the text.

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

ח

0.85

ד

0.85

ח

0.77

 CHARACTER

0.75

 Accessed

0.75

 remainder

0.75

↵↵

0.70

 اﻷ

0.69

 תו

0.68

↵

0.66

POSITIVE LOGITS

zeti

0.80

 Saheb

0.80

↺

0.79

 abbey

0.79

アルバム

0.78

ма

0.78

 jours

0.77

យើង

0.75

objc

0.75

jours

0.75

Activations Density 0.000%