INDEX

Explanations

training workshops

The main thing this neuron does is detect mentions of workshops and similar training or educational event terms.

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

-1.88

 alarme

-1.59

 somewhat

-1.47

罽

-1.46

 trajo

-1.44

 dacht

-1.43

 calça

-1.42

 intuitively

-1.42

 espé

-1.41

驺

-1.40

POSITIVE LOGITS

ції

1.76

();

1.59

1.55

 để

1.54

,”

1.53

…”

1.53

 כדי

1.51

}}

1.48

鲜血

1.47

。”

1.46

Activations Density 0.014%