INDEX

Explanations

always followed by action

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

winding

1.59

ة

1.54

ፍተኛ

1.52

usive

1.48

 lingue

1.41

Ꮙ

1.39

}$).

1.37

р

1.32

tej

1.32

ция

1.30

POSITIVE LOGITS

ு

1.56

nach

1.43

 κατο

1.40

 shorth

1.38

lessly

1.36

 dotyczą

1.31

 usize

1.29

符

1.29



1.28

 hesitated

1.27

Activations Density 0.002%