INDEX

Explanations

lock down and place names

model weights, not, cannot

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

 космети

0.46

ේ

0.46

 정의

0.46

시

0.45

 Donations

0.45

 defined

0.45

 Defined

0.44

 자신

0.43

티

0.43

러

0.43

POSITIVE LOGITS

 SOCKET

0.44

 resistances

0.43

 harte

0.43

 apopt

0.42

 resisting

0.42

 Gött

0.42

 ويل

0.42

ربي

0.41

آور

0.40

 امد

0.40

Activations Density 0.000%