INDEX

Explanations

migration and directional movement

The neuron detects the word "migration" and related concepts in scientific/medical contexts.

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

 that

-1.67

谎

-1.51

-1.41

-1.38

「

-1.36

졌

-1.35

 muñeco

-1.34

ものの

-1.32

 этому

-1.31

«

-1.29

POSITIVE LOGITS

 into

2.03

摑

1.72

 toward

1.67

Seznam

1.55

恥

1.53

鼉

1.52

cinnati

1.47

 towards

1.46

をご覧ください

1.41

 regels

1.41

Activations Density 0.132%