INDEX

Explanations

words starting with Le

The neuron selectively activates on the subword “Le” (e.g. as a standalone or word‐piece token beginning with “Le”).

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

 pagine

-0.89

ี่ยม

-0.89

ringar

-0.82

 Monats

-0.82

-0.78

 meinem

-0.77

 prevista

-0.77

 istruzioni

-0.75

ect

-0.75

隙間

-0.73

POSITIVE LOGITS

 Ле

1.34

Le

1.29

Lé

1.23

Le

1.23

Ле

1.22

lə

1.12

LEV

0.96

 obé

0.96

LE

0.94

LE

0.93

Activations Density 0.042%