Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    nested parentheses or brackets in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ―――――
    -2.18
     Theſe
    -2.15
     itſelf
    -2.14
     myſelf
    -2.10
    BibitemShut
    -2.04
     Anſ
    -1.95
     iſt
    -1.94
    ſelf
    -1.87
    leſs
    -1.84
     Reſ
    -1.83
    POSITIVE LOGITS
    (
    3.65
     (
    1.97
    [
    1.88
    ("
    1.82
    （
    1.75
    {
    1.67
    ('
    1.59
    (\
    1.56
    ()
    1.48
    =
    1.48
    Act Density 0.450%

    No Known Activations