INDEX

Explanations

event timing

The neuron activates on numeric tokens (years, counts, percentages, and other figures).

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

-1.15

event

-1.10

opt

-1.05

test

-1.04

market

-1.04

non

-1.03

min

-0.98

open

-0.97

abs

-0.96

POSITIVE LOGITS

 last

2.09

 recent

1.90

 April

1.75

 recently

1.74

 today

1.61

 yesterday

1.58

 January

1.55

 November

1.49

 December

1.44

 September

1.42

Activations Density 0.070%