INDEX

Explanations

time periods

The neuron responds to standalone numeric tokens (especially multi‐digit numbers and decimals). In other words, it detects numerical values.

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

-2.00

垸

-1.87

绒

-1.80

 condenado

-1.72

隳

-1.69

 Alquiler

-1.67

 Unidades

-1.63

 Nuevas

-1.58

༵

-1.56

 velikost

-1.55

POSITIVE LOGITS

 других

1.77

te

1.73

ta

1.73

 jonka

1.72

of

1.70

–

1.68

1.67

 period

1.66

 التي

1.66

та

1.65

Activations Density 0.025%