INDEX

Explanations

classification, category, or specific numbers

The neuron fires in contexts that mention traveling or trips to foreign countries.

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

postion

0.92

 하지만

0.91

gallon

0.91

Eligibility

0.89

Alumno

0.89

 Entretanto

0.89

 Probate

0.88

ସ

0.87

କୁ

0.86

Anybody

0.86

POSITIVE LOGITS

 conditionally

1.30

с

1.27

і

1.21

 її

1.21

 incompre

1.20

и

1.18

 от

1.16

 по

1.15

 analogues

1.13

н

1.13

Activations Density 0.267%