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

 ramp

1.24

agun

1.19

 건축

1.15

갯

1.14

ثله

1.13

 compared

1.11

컸

1.09

 damal

1.08

쌈

1.08

룻

1.07

POSITIVE LOGITS

 Consecutive

1.59

 consecutive

1.41

 consecut

1.20

 consecutivos

1.17

 Simultaneous

1.13

째

1.11

inuous

1.09

geqslant

1.06

Repeating

1.05

 alternating

1.04

Activations Density 0.122%

No Known Activations