INDEX

Explanations

several

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

 ſeveral

-0.91

various

-0.84

 feveral

-0.77

$.

-0.76

Various

-0.75

several

-0.72

)";

-0.71

.";

-0.70

noinspection

-0.70

 various

-0.69

POSITIVE LOGITS

 types

0.75

 times

0.71

 things

0.60

 kinds

0.59

 levels

0.58

 amounts

0.58

 hundred

0.56

########.

0.53

of

0.52

 ways

0.52

Activations Density 0.039%