INDEX

Explanations

actual / specifically

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

issa

-0.95

it

-0.92

月的

-0.83

デザ

-0.81

啖

-0.78

とい

-0.77

 }^{*}

-0.77

 preocupar

-0.76

quée

-0.75

assen

-0.74

POSITIVE LOGITS

 actual

1.61

Specifically

1.17

真正的

1.13

Actual

1.08

hône

1.05

 específicamente

1.03

 actually

1.02

 echte

1.01

 ACTUAL

1.01

strahlung

1.00

Activations Density 0.102%