INDEX

Explanations

predicting the next word

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

omitempty

0.50

Experience

0.49

čně

0.46

Responding

0.46

('

0.46

ومین

0.46

Utt

0.45

Apr

0.45

Ą

0.45

POSITIVE LOGITS

 blacklist

0.52

ين

0.49

 credibility

0.48

 tormented

0.46

 martyr

0.45

 spectator

0.44

ра

0.44

 twist

0.44

 tangled

0.43

 mentality

0.43

Activations Density 0.062%