INDEX

Explanations

viagra

spam content and artificially inserted text in otherwise normal content.

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

小程序

-0.85

usermodel

-0.85

 festen

-0.84

DESCRIPCIÓN

-0.84

Ці

-0.82

 amusing

-0.77

empêcher

-0.75

ー

-0.75

 Ebony

-0.74

 fundamentally

-0.72

POSITIVE LOGITS

cbd

1.00

髭

0.93

 viagra

0.92

 miền

0.91

 шокола

0.90

CBD

0.88

 stroom

0.87



0.86

TURN

0.86



0.85

Activations Density 0.029%