INDEX

Explanations

plant stems

The neuron detects mentions of plant stems or similar stalk-like structures.

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

-1.90

acious

-1.45

</b>

-1.38

 bidra

-1.38

LAHOMA

-1.35

 woorden

-1.34

pas

-1.33

<i>

-1.33

-1.32

POSITIVE LOGITS

 kurzem

1.70

 cómo

1.63

屹

1.61

 Когда

1.59

 hallowed

1.50

 budding

1.47

 cuánto

1.46

 Whenever

1.45

⚋

1.43

後記

1.42

Activations Density 0.033%