INDEX

Explanations

Lowercase then uppercase letters

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 kaarangay

-0.72

 виправивши

-0.67

 esternos

-0.66

:✨

-0.65

 typelib

-0.64

 cherchés

-0.62

enumii

-0.56

NameInMap

-0.55

Tikang

-0.54

twimg

-0.52

POSITIVE LOGITS

kd

0.91

jd

0.80

Qd

0.80

gd

0.79

KD

0.79

fd

0.79

SFD

0.79

sd

0.77

KD

0.77

bd

0.76

Activations Density 0.001%