INDEX

Explanations

seasons and causes

This neuron activates on standalone, heading‐style tokens (often title‐case or section‐label words) that appear at the start of lines or document sections.

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

↵

-1.54

not

-1.37

 whose

-1.23

 That

-1.19

 which

-1.18

 ikke

-1.17

 însă

-1.13

melden

-1.12

しない

-1.11

ற்ப

-1.11

POSITIVE LOGITS

﹌

1.40

 berücksich

1.37

Também

1.30

ashvili

1.27

@[+][

1.27

QWidget

1.25

 verbessern

1.23

@"/

1.23

ForType

1.23

 maroon

1.23

Activations Density 0.104%