INDEX

Explanations

analyzing and predicting behavior

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

<unused2197>

1.16

 Außerdem

1.09

хий

1.05

<unused2172>

1.03

ayvachi

1.02

ágenes

1.01

apadani

1.01

гах

1.01

<unused2223>

1.00

braith

1.00

POSITIVE LOGITS

not

0.78

 bukan

0.77

 augmented

0.76

 simulation

0.76

 sandalwood

0.76

 density

0.73

 teoria

0.71

 dode

0.70

 verbose

0.69

 olfactory

0.69

Activations Density 0.022%