INDEX

Explanations

scene graph

The neuron strongly responds to occurrences of the identifier “scene” (i.e. the variable or property name “scene”) in code.

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

 utilisée

-2.16

婞

-2.11

谂

-2.03

 Bemerkungen

-2.02

 tocó

-2.02

zembro

-2.00

맏

-1.97

 nuovamente

-1.95



-1.90

怎么可能

-1.88

POSITIVE LOGITS

3.30

2.16

...

2.11

↵↵

2.03

2.02

2.00

1.98

<bos>

1.98

1.95

1.93

Activations Density 0.004%