INDEX

Explanations

css units and units abbreviations

The neuron flags standalone numeric tokens (literal numbers) in the text.

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

 pixels

-0.97

 metody

-0.84

recruit

-0.82

 tesettür

-0.79

aspx

-0.78

Hats

-0.78

astră

-0.77

塙

-0.76

 shown

-0.76

reboot

-0.76

POSITIVE LOGITS

 บาท

0.93

 commutative

0.90

再

0.89

_:

0.88

__);

0.84

公式

0.84

","

0.81

THREE

0.81

Two

0.80

Computer

0.80

Activations Density 0.015%