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

    Neuronpedia

    INDEX
    Explanations

    parentheses and other related punctuation used in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     "..\..\
    -0.65
    ########.
    -0.65
    protoimpl
    -0.61
    IUrlHelper
    -0.60
    <blockquote>
    -0.59
    complexContent
    -0.59
    IntoConstraints
    -0.57
    Parcelize
    -0.57
    marvin
    -0.56
    +#+
    -0.55
    POSITIVE LOGITS
    (_
    2.42
     (_
    2.12
    [_
    1.88
    >(_
    1.74
    =_
    1.59
     [_
    1.57
     (!_
    1.40
    <_
    1.33
    :_
    1.29
    (!_
    1.27
    Act Density 0.287%

    No Known Activations