INDEX

Explanations

conditional statements involving hypothetical scenarios or examples

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

atak

-0.07

 neither

-0.06

à¸±à¸¨à¸Ļ

-0.06

illon

-0.06

_almost

-0.06

 Neither

-0.06

 sometimes

-0.05

Î»Î±Î½

-0.05

 atleast

-0.05

 paved

-0.05

POSITIVE LOGITS

 ÙħØ«ÙĦØ§

0.09

 someone

0.09

someone

0.09

 somebody

0.08

say

0.08

 Incontri

0.07

Ð½Ð°Ð¹

0.07

ä¸Ģä¸ªäºº

0.07

æŁĲ

0.07

Activations Density 0.021%