INDEX

Explanations

B2B, e2e, MLM

The neuron fires on short acronyms where “2” connects two letter groups (e.g. B2B, M2M, p2p, e2e, P2P, C2C).

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

is

-2.36

 will

-2.00

聼

-1.95

 worauf

-1.91

has

-1.88

 there

-1.88

can

-1.87

);

-1.84

 positioned

-1.80

 termed

-1.77

POSITIVE LOGITS

 置物

2.06

</strong>

1.96

で

1.87

as

1.86

AC

1.84

時に

1.84

ſelves

1.80

 gömlek

1.78

1.75

 preciosas

1.74

Activations Density 0.003%