INDEX

Explanations

themes related to anthropomorphism and emotional responses to characters and situations

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

 Particip

-0.08

Req

-0.07

rary

-0.07

ream

-0.07

cec

-0.06

plode

-0.06

quential

-0.06

Intialized

-0.06

YD

-0.06

regn

-0.06

POSITIVE LOGITS

 human

0.08

human

0.07

 humanoid

0.07

-human

0.07

 humans

0.06

 near

0.06

.Interface

0.06

Human

0.06

 Harmony

0.06

Î¯Î½Î±

0.06

Activations Density 0.000%