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

le

0.89

mium

0.87

ّد

0.79

uple

0.79

ко

0.76

일부터

0.75

па

0.74

団

0.74

on

0.73

入

0.72

POSITIVE LOGITS

 policymakers

1.35

 chercheurs

1.35

 ecologists

1.31

 researchers

1.31

 anthropologists

1.25

 commentators

1.24

 Routledge

1.24

 Regan

1.24

 Researchers

1.23

Researchers

1.23

Activations Density 0.074%

No Known Activations