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

    Neuronpedia

    INDEX
    Explanations

    negations or instances where actions are not being taken

    oai_token-act-pair · gpt-3.5-turbo

    negative constructions and phrases indicating lack of action or responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CST
    -0.72
    eers
    -0.70
    soDeliveryDate
    -0.70
     Mehran
    -0.70
     Valhalla
    -0.69
     Cth
    -0.67
     Geh
    -0.65
     Tant
    -0.65
     Tribune
    -0.64
     Ninth
    -0.63
    POSITIVE LOGITS
     accepting
    0.94
    paying
    0.93
    pleting
    0.93
    iating
    0.93
    angering
    0.93
     rewarding
    0.90
     agreeing
    0.90
     committing
    0.89
    having
    0.89
     engaging
    0.88
    Act Density 0.189%

    No Known Activations