INDEX

Explanations

atom, block, rocks, tensor, equation

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

те

1.69

 Якщо

1.56

حمد

1.55

การ

1.52

 eccess

1.51

غ

1.49

ני

1.45

ćeg

1.45

 afield

1.43

 avanzando

1.41

POSITIVE LOGITS

1.84

1.77

ipated

1.57

muster

1.49

owment

1.44

speaker

1.40

moy

1.34

she

1.34

ipe

1.32

后来

1.27

Activations Density 0.001%