INDEX

Explanations

jour JOUR JOURneys

The neuron activates on numeric tokens and figures, detecting quantities and numbers (including decimal values).

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

IUrlHelper

-1.55

 esclusivamente

-1.47

 множество

-1.41

 leggermente

-1.41

ضی

-1.39

 forsaken

-1.38

⅜

-1.37

.}(

-1.34

プライズ

-1.34

 republicans

-1.33

POSITIVE LOGITS

iling

1.38

of

1.38

ほら

1.38

 perguntou

1.36

mẫu

1.35

过来了

1.34

 slipped

1.34

bonsoir

1.33

 encantador

1.33

 respondeu

1.33

Activations Density 0.037%