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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and relationships in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    >\<^
    -0.66
     كومونز
    -0.65
    UFACT
    -0.64
    ^(@)
    -0.64
    kug
    -0.61
     onPause
    -0.59
     UITableViewCell
    -0.59
    iosync
    -0.58
    setupUi
    -0.58
    NSNotification
    -0.57
    POSITIVE LOGITS
     […]
    1.99
    ↵
    1.83
     [...]
    1.56
    ,...
    1.54
    <eos>
    1.47
    ...
    1.47
    ↵↵
    1.40
    [...]
    1.40
    […]
    1.38
     ..."
    1.36
    Act Density 9.162%

    No Known Activations