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

    Neuronpedia

    INDEX
    Explanations

    specific discourse elements indicating structure or sequence in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     utafitiHapana
    -0.68
    toolStripButton
    -0.64
    onResume
    -0.58
     BoxFit
    -0.57
    たまた
    -0.57
    intenant
    -0.55
    bbene
    -0.54
    LError
    -0.54
     CanadaChoose
    -0.54
     sonno
    -0.54
    POSITIVE LOGITS
    ↵↵↵
    0.84
    省市镇
    0.81
    <bos>
    0.80
    <eos>
    0.78
    RegressionTest
    0.78
    InjectAttribute
    0.76
    UnsafeEnabled
    0.69
    ↵↵↵↵
    0.67
     вікі
    0.66
    webElementXpaths
    0.66
    Act Density 0.545%

    No Known Activations