INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

:"",

1.40

..");

1.33

()");

1.32

。",

1.31

）』

1.30

='"+

1.30

...");

1.25

...');

1.25

.",

1.25

=");

1.24

POSITIVE LOGITS

↵↵

4.48

↵↵↵

3.16

↵↵↵↵

3.01

↵↵↵↵↵

2.76

<start_of_image>

2.76

↵↵↵↵↵↵

2.59

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

2.48

↵↵↵↵↵↵↵

2.46

↵↵↵↵↵↵↵↵

2.43

<eos>

2.40

Activations Density 8.351%

No Known Activations