INDEX

Explanations

documentation headers

The neuron is keyed to isolated backslash characters (e.g. in Doxygen or similar documentation commands).

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

to

-1.97

.”

-1.97

 Already

-1.54

 '\''

-1.48

].

-1.47

–

-1.44

了不少

-1.40

锁

-1.40

 reciben

-1.38

 Untersuch

-1.35

POSITIVE LOGITS

 також

1.91

鹮

1.66

 myös

1.66

 violen

1.59

Mitar

1.58

 aussi

1.56

 also

1.52

Rujukan

1.52

糟糕

1.51

⍽

1.49

Activations Density 0.010%