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

    Neuronpedia

    INDEX
    Explanations

    keywords related to canceling or discontinuing an action or event

    oai_token-act-pair · gpt-3.5-turbo

    commands related to cancelation or continuation of content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    teenth
    -0.82
    ILY
    -0.80
     snipp
    -0.71
    lycer
    -0.71
    MpServer
    -0.67
    女
    -0.64
     distribut
    -0.64
     scarce
    -0.64
    velt
    -0.63
    gt
    -0.63
    POSITIVE LOGITS
     Cancel
    0.90
     button
    0.86
    button
    0.86
    ification
    0.80
     Button
    0.80
    ify
    0.77
    uation
    0.75
    ning
    0.72
    icted
    0.72
    uters
    0.71
    Act Density 0.036%

    No Known Activations