INDEX

Explanations

little/small followed by noun

The neuron responds to diminutive size words—especially “little” (and similarly “small” or “short”).

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

 instead

-1.27

 största

-1.26

 Instead

-1.25

と

-1.22

 diverso

-1.21

 niyang

-1.21

 новым

-1.20

 vielfäl

-1.20

 assunto

-1.18

íše

-1.17

POSITIVE LOGITS

[]:

1.77

).

1.32

 بودند

1.30

 эффективность

1.30

瀋

1.28

')"

1.27

 costuras

1.25

",

1.25

onora

1.22

but

1.21

Activations Density 0.049%