INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

들과

1.30

仕組み

1.26

 και

1.23

roffen

1.20

海道

1.19

기와

1.18

и

1.17

 થય

1.17

 দফা

1.15

oughby

1.14

POSITIVE LOGITS

 scanned

1.18

 ghost

1.11

convolution

1.07

ghost

1.07

 prove

1.06

vom

1.06

 tane

1.06

 uncut

1.05

 ghosts

1.05

 Suicide

1.04

Activations Density 0.000%

No Known Activations