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

    Neuronpedia

    INDEX
    Explanations

    text related to legal proceedings

    oai_token-act-pair · gpt-3.5-turbo

    instances of interruptions during formal events or speeches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     murders
    -0.83
     winters
    -0.82
    agate
    -0.81
    soDeliveryDate
    -0.74
     adventures
    -0.74
    profits
    -0.73
     [&
    -0.73
    Month
    -0.72
    ondon
    -0.72
     Monthly
    -0.70
    POSITIVE LOGITS
     applause
    1.69
     cheers
    1.33
     chants
    1.26
     seated
    1.24
     podium
    1.24
     visibly
    1.22
     onstage
    1.21
     shouted
    1.19
     chanted
    1.18
     hugged
    1.17
    Act Density 0.959%

    No Known Activations