INDEX

Explanations

wandering or roaming

The neuron flags words that express aimless or wandering movement (e.g. wandering, pacing, roaming, lost).

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



-2.28

糴

-2.17

雠

-2.11

饪

-2.08

 envíos

-2.05

 suministros

-2.00



-1.86

 Kamis

-1.84



-1.83

たまた

-1.81

POSITIVE LOGITS

in

2.84

for

2.05

 have

2.03

 wandering

1.98

 Where

1.88

on

1.85

\}}

1.74

Our

1.69

are

1.66

鉀

1.66

Activations Density 0.014%