INDEX

Explanations

direction

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

 direction

-1.03

 Direction

-1.00

 DIRECTION

-0.93

Direction

-0.90

direction

-0.84

DIRECTION

-0.79

 arah

-0.75

 directions

-0.74

 direzione

-0.66

方向

-0.65

POSITIVE LOGITS

ality

0.93

 CreateTagHelper

0.87

alities

0.82

ALITY

0.76

ally

0.68

MessageOf

0.66

alty

0.64

 SEDS

0.59

marshaller

0.59

ніципа

0.59

Activations Density 0.049%