INDEX

Explanations

words starting with nom

The neuron activates on any occurrence of the letter sequence “nom” (in any case) within a token.

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

there

-3.30

觧

-2.98

荭

-2.97

岽

-2.97

阄

-2.94

gráficas

-2.88

珦

-2.73

乆

-2.63

:");

-2.61

</td>

-2.59

POSITIVE LOGITS

 sizzling

2.50

没有

2.50

</strong>

2.44

 あります

2.41

繰り返

2.31

er

2.31

又

2.30

 屋根

2.28

 feront

2.25

✳

2.22

Activations Density 0.003%