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

    Neuronpedia

    INDEX
    Explanations

    comments and notes indicating tasks or changes within code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <b>
    -0.63
    <strong>
    -0.61
    <eos>
    -0.58
    parsedMessage
    -0.58
    .”
    -0.56
    InstanceState
    -0.56
    stateProvider
    -0.56
    ”.
    -0.56
    %;">
    -0.52
     }}"></
    -0.52
    POSITIVE LOGITS
     uncomment
    0.87
     FIXME
    0.80
     hack
    0.78
     commented
    0.75
     why
    0.74
    BUG
    0.72
     probably
    0.71
     TODO
    0.70
    暂时
    0.69
     need
    0.69
    Act Density 0.671%

    No Known Activations